© 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. 126142
    Prev
    Next
    INDEX
    Explanations

    rankings/lists/awards

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that are part of numeric rankings or list‐name phrases (e.g. “Inc. 5000,” top-X lists, and similar ranked-company mentions).

    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
     Polymer
    -0.07
     Procedures
    -0.07
     Ra
    -0.07
     vanish
    -0.07
    pawn
    -0.06
    embrance
    -0.06
     أمر
    -0.06
     Plymouth
    -0.06
    ief
    -0.06
    .signIn
    -0.06
    POSITIVE LOGITS
    UIImage
    0.07
    .Fixed
    0.06
    lilik
    0.06
     specialized
    0.06
    .temp
    0.06
    %);↵
    0.06
    .Fatalf
    0.06
    .getColor
    0.06
    isin
    0.06
    Views
    0.06
    Activations Density 0.042%

    No Known Activations