© 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 (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 31651
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    捕
    -0.07
     cuk
    -0.07
    —I
    -0.07
     vocal
    -0.06
    ->$
    -0.06
    -plane
    -0.06
    752
    -0.06
    _lowercase
    -0.06
     docking
    -0.06
    Metal
    -0.06
    POSITIVE LOGITS
     dưỡng
    0.06
     TreeNode
    0.06
    FirstResponder
    0.06
     prevailed
    0.06
     pornos
    0.06
     origins
    0.06
    .red
    0.06
    OLD
    0.06
     stra
    0.06
     AF
    0.06
    Activations Density 0.097%

    No Known Activations