© 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
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 32636
    Prev
    Next
    INDEX
    Explanations

    Earning and paying

    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
    (instr
    -0.07
    skému
    -0.06
    нок
    -0.06
    .cast
    -0.06
     luyện
    -0.06
    HITE
    -0.06
     Err
    -0.06
    .WRITE
    -0.06
    progress
    -0.06
     IDD
    -0.06
    POSITIVE LOGITS
     tres
    0.07
    .rdf
    0.07
     teď
    0.07
    Louis
    0.06
    .gdx
    0.06
    733
    0.06
     preceding
    0.06
    Camera
    0.06
    getString
    0.06
     supportive
    0.06
    Activations Density 0.021%

    No Known Activations