Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 45310
    Prev
    Next
    INDEX
    Explanations

    Flask

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stanley
    -0.07
    =output
    -0.07
    Provid
    -0.06
    ayas
    -0.06
    India
    -0.06
     Guy
    -0.06
    국의
    -0.06
     يق
    -0.06
     de
    -0.06
     Provid
    -0.06
    POSITIVE LOGITS
    lica
    0.06
    тив
    0.06
    .al
    0.06
     ジャ
    0.06
     ObjectId
    0.06
    SpinBox
    0.06
     Horizon
    0.06
     кисл
    0.06
     Monica
    0.06
    РИ
    0.06
    Activations Density 0.001%

    No Known Activations