© 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. 15-RESID-POST-AA
    11. 312
    Prev
    Next
    INDEX
    Explanations

    100

    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
     теч
    -0.06
    िषय
    -0.06
    ारण
    -0.06
    ivent
    -0.06
    .axes
    -0.06
    匹
    -0.06
    -product
    -0.06
     chest
    -0.06
     mín
    -0.06
    -project
    -0.06
    POSITIVE LOGITS
     уд
    0.06
    <section
    0.06
    ailed
    0.06
     Heidi
    0.06
    .Error
    0.06
     interceptions
    0.06
    UTION
    0.06
     기다
    0.06
    =False
    0.06
     Lovely
    0.06
    Activations Density 0.000%

    No Known Activations