© 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. 15-RESID-POST-AA
    6. 34265
    Prev
    Next
    INDEX
    Explanations

    libraries

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SAM
    -0.07
    _spacing
    -0.07
     tg
    -0.07
    "W
    -0.07
     beh
    -0.06
    直
    -0.06
     gap
    -0.06
    join
    -0.06
    Stra
    -0.06
    ?!↵↵
    -0.06
    POSITIVE LOGITS
    .prototype
    0.07
     示例
    0.06
    B
    0.06
     hidden
    0.06
     francais
    0.06
    ernetes
    0.06
     renown
    0.06
     chevy
    0.06
     diagnose
    0.06
     GenerationType
    0.06
    Activations Density 0.061%

    No Known Activations