© 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. 7-RESID-POST-AA
    11. 86217
    Prev
    Next
    INDEX
    Explanations

    gas

    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
     anak
    -0.07
    ogs
    -0.07
    ãy
    -0.06
    igte
    -0.06
    イド
    -0.06
    enie
    -0.06
    isiert
    -0.06
     animals
    -0.06
    クラ
    -0.06
    巧
    -0.06
    POSITIVE LOGITS
    !*
    0.06
    $info
    0.06
    بش
    0.06
     Assass
    0.06
     zz
    0.06
    objectId
    0.06
    ;!
    0.06
     runApp
    0.06
     gi
    0.06
    PermissionsResult
    0.06
    Activations Density 0.003%

    No Known Activations