© 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
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 39841
    Prev
    Next
    INDEX
    Explanations

    basketball

    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
     neurons
    -0.07
    _confirmation
    -0.07
    headline
    -0.07
    yy
    -0.07
     Clown
    -0.06
    .Update
    -0.06
     Tooth
    -0.06
     ölçü
    -0.06
    时代
    -0.06
    Telefono
    -0.06
    POSITIVE LOGITS
     basket
    0.17
     Basket
    0.15
    -basket
    0.12
     baskets
    0.10
    Basket
    0.10
    basket
    0.10
     cest
    0.08
    송
    0.08
    -box
    0.07
    543
    0.07
    Activations Density 0.002%

    No Known Activations