© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 14290
    Prev
    Next
    INDEX
    Explanations

    4

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    codegen
    -0.06
    =
    -0.06
    timezone
    -0.06
     "`
    -0.06
    ючись
    -0.06
    )%
    -0.06
     whitespace
    -0.06
    ouv
    -0.06
     PhoneNumber
    -0.06
    이크
    -0.06
    POSITIVE LOGITS
    Pel
    0.07
     classify
    0.06
    !'↵
    0.06
     "\<
    0.06
    .PORT
    0.06
    _terms
    0.06
     symptom
    0.06
     انگ
    0.06
     순간
    0.06
    \Carbon
    0.06
    Activations Density 0.028%

    No Known Activations