© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 35280
    Prev
    Next
    INDEX
    Explanations

    summary

    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
    につ
    -0.07
     Получ
    -0.06
     орган
    -0.06
     repro
    -0.06
     autof
    -0.06
    iment
    -0.06
    申请
    -0.06
    _edit
    -0.06
    ency
    -0.06
    Collector
    -0.06
    POSITIVE LOGITS
     CG
    0.06
    Wie
    0.06
    .RowStyle
    0.06
    *A
    0.06
    (Collision
    0.06
    *L
    0.06
     Mary
    0.06
    乌
    0.06
    .swt
    0.06
     Monad
    0.06
    Activations Density 0.110%

    No Known Activations