© 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. 93248
    Prev
    Next
    INDEX
    Explanations

    Letter D/d or 4

    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
     الخارج
    -0.06
     tonnes
    -0.06
     Worm
    -0.06
    熱
    -0.06
    ़र
    -0.06
     북
    -0.06
     lhs
    -0.06
     умови
    -0.06
     wt
    -0.06
     spelling
    -0.06
    POSITIVE LOGITS
    кап
    0.07
     cutter
    0.06
    {{{
    0.06
     гар
    0.06
    _DEN
    0.06
     Draws
    0.06
    ardi
    0.06
     depicting
    0.06
    ,v
    0.06
     степ
    0.06
    Activations Density 0.013%

    No Known Activations