© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 52996
    Prev
    Next
    INDEX
    Explanations

    academic essays/articles

    np_max-act · gemini-2.0-flash

    This neuron is essentially a sentence-structure detector: it lights up on punctuation marks (commas, periods, colons) and the capitalized tokens that begin new sentences or clauses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    discussions about the impact of emerging technologies, particularly in the context of media and society.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     хочу
    -0.06
     earnest
    -0.06
    771
    -0.06
    Forgot
    -0.06
    INVALID
    -0.06
     CVS
    -0.06
    ;
↵
↵
    -0.06
    ourse
    -0.06
    -object
    -0.06
    Band
    -0.06
    POSITIVE LOGITS
    	BufferedReader
    0.07
    anvas
    0.07
    AreaView
    0.06
     fraternity
    0.06
    //================================================================
    0.06
    .urls
    0.06
     číslo
    0.06
     یوتی
    0.06
    oa
    0.06
    .Atomic
    0.06
    Activations Density 0.193%

    No Known Activations