© 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. 697
    Prev
    Next
    INDEX
    Explanations

    predis

    np_max-act · gemini-2.0-flash

    The neuron responds to occurrences of the root “predispos-” (as in predispose, predisposition, etc.), flagging mentions of factors that make an outcome more likely.

    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
    _lost
    -0.06
     paragraph
    -0.06
    机械
    -0.06
    -Oct
    -0.06
     Butter
    -0.06
     otom
    -0.06
     counting
    -0.06
    _CLI
    -0.06
    IFA
    -0.06
     Sierra
    -0.06
    POSITIVE LOGITS
     predis
    0.11
    .readlines
    0.07
     handicap
    0.07
    тех
    0.06
    is
    0.06
    Ư
    0.06
    ngle
    0.06
    (prefix
    0.06
    ни
    0.06
    iw
    0.06
    Activations Density 0.003%

    No Known Activations