© 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. 7-RESID-POST-AA
    6. 94564
    Prev
    Next
    INDEX
    Explanations

    conversational speech

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    于是
    -0.07
     prendre
    -0.06
     sue
    -0.06
     hai
    -0.06
     flavours
    -0.06
    fm
    -0.06
    Researchers
    -0.06
    MY
    -0.06
    'h
    -0.06
    ایش
    -0.06
    POSITIVE LOGITS
     continental
    0.07
    &B
    0.06
    .WriteAllText
    0.06
     MatDialog
    0.06
    <Pair
    0.06
     stip
    0.06
     Jwt
    0.06
     Herb
    0.06
    (prop
    0.06
     EdgeInsets
    0.06
    Activations Density 0.072%

    No Known Activations