© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125016
    Prev
    Next
    INDEX
    Explanations

    contribute

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens and adjacent words in statistics or metrics, i.e. it spots numbers (dates, counts, quantities) and their immediate context.

    oai_token-act-pair · o4-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
    585
    -0.07
     Lift
    -0.06
    intendo
    -0.06
    чного
    -0.06
     Simply
    -0.06
     Gordon
    -0.06
     Highland
    -0.06
    683
    -0.06
     таким
    -0.06
    할
    -0.06
    POSITIVE LOGITS
    ụ
    0.07
     Antoine
    0.07
     remar
    0.07
     criticized
    0.07
     Ül
    0.07
    AdapterFactory
    0.07
     za
    0.06
    .Writer
    0.06
    	dd
    0.06
     Contrib
    0.06
    Activations Density 0.025%

    No Known Activations