© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110258
    Prev
    Next
    INDEX
    Explanations

    bowl

    np_max-act · gemini-2.0-flash

    instructions related to cancer staging and clinical data extraction.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron does not respond to any text patterns—it remains inactive on all tokens.

    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
    -three
    -0.07
    Oops
    -0.07
    sharing
    -0.06
     massac
    -0.06
    ,s
    -0.06
     payment
    -0.06
    filesize
    -0.06
     brut
    -0.06
    _unsigned
    -0.06
     bw
    -0.06
    POSITIVE LOGITS
     Additionally
    0.08
     merupakan
    0.07
     Rubin
    0.07
     reinforce
    0.06
    ATTERN
    0.06
     Hancock
    0.06
     зел
    0.06
     Removal
    0.06
    /run
    0.06
     implies
    0.06
    Activations Density 0.000%

    No Known Activations