© 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. 40521
    Prev
    Next
    INDEX
    Explanations

    exercise

    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
    OwnProperty
    -0.07
    .body
    -0.07
    ehler
    -0.07
    aison
    -0.06
     amaç
    -0.06
     layer
    -0.06
    Normals
    -0.06
     Azerbaijan
    -0.06
     avenues
    -0.06
    ais
    -0.06
    POSITIVE LOGITS
    드는
    0.07
     العم
    0.07
     diagon
    0.06
    ınma
    0.06
    xef
    0.06
    を
    0.06
     adjoining
    0.06
     blush
    0.06
     sincerely
    0.06
     челов
    0.06
    Activations Density 0.006%

    No Known Activations