© 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. 3-RESID-POST-AA
    11. 121652
    Prev
    Next
    INDEX
    Explanations

    economic hardship

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     μο
    -0.07
    _icall
    -0.07
    不可
    -0.07
    _tooltip
    -0.07
    BigDecimal
    -0.06
    �
    -0.06
    jsonData
    -0.06
    ASS
    -0.06
    合作
    -0.06
     death
    -0.06
    POSITIVE LOGITS
     recession
    0.07
    atings
    0.06
     aust
    0.06
    nění
    0.06
     grammar
    0.06
    ars
    0.06
     edeb
    0.06
    rze
    0.06
    ectar
    0.06
    .ResultSet
    0.06
    Activations Density 0.182%

    No Known Activations