© 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. 111663
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Os
    -0.06
     Britann
    -0.06
     Db
    -0.06
     mô
    -0.06
    _Global
    -0.06
    _DU
    -0.06
    الف
    -0.06
    mmas
    -0.06
    Vals
    -0.06
    67
    -0.06
    POSITIVE LOGITS
    andez
    0.07
     cushions
    0.07
     cushion
    0.06
    irez
    0.06
     prakt
    0.06
    ACL
    0.06
     cir
    0.06
     uživatel
    0.06
    .SaveChangesAsync
    0.06
    .walk
    0.06
    Activations Density 0.055%

    No Known Activations