© 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. 15-RESID-POST-AA
    6. 83507
    Prev
    Next
    INDEX
    Explanations

    Date

    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
     paperback
    -0.07
     آبی
    -0.07
    .lbl
    -0.07
    Η
    -0.06
     HttpMethod
    -0.06
    Affected
    -0.06
    itness
    -0.06
    .getFont
    -0.06
     ddl
    -0.06
    (','
    -0.06
    POSITIVE LOGITS
     zipfile
    0.06
    薩
    0.06
     Samoa
    0.06
    ando
    0.06
    step
    0.06
    зн
    0.06
     Pastor
    0.06
     partially
    0.06
     Isles
    0.06
    iron
    0.06
    Activations Density 0.000%

    No Known Activations