© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 76581
    Prev
    Next
    INDEX
    Explanations

    Company identifiers

    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_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
    があり
    -0.07
    ちょっと
    -0.06
    UNT
    -0.06
     superb
    -0.06
    かり
    -0.06
    ONE
    -0.06
    alten
    -0.06
    Liverpool
    -0.06
    .phone
    -0.06
     kém
    -0.06
    POSITIVE LOGITS
    niž
    0.07
    <|begin_of_text|>
    0.06
    mino
    0.06
     Smart
    0.06
    ToBounds
    0.06
    ение
    0.06
    ское
    0.06
     Scalars
    0.06
     너무
    0.06
     Clips
    0.06
    Activations Density 0.016%

    No Known Activations