© 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. 113683
    Prev
    Next
    INDEX
    Explanations

    diagram

    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
     окт
    -0.07
     voi
    -0.06
     carga
    -0.06
    .vx
    -0.06
    enville
    -0.06
    SEX
    -0.06
    Health
    -0.06
    mult
    -0.06
    jango
    -0.06
    ือข
    -0.06
    POSITIVE LOGITS
     diagram
    0.18
     diagrams
    0.18
    Diagram
    0.14
     Diagram
    0.14
     sacram
    0.07
    図
    0.07
    Fig
    0.07
     digging
    0.07
     decom
    0.07
     aspir
    0.07
    Activations Density 0.003%

    No Known Activations