© 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. 11-RESID-POST-AA
    6. 93521
    Prev
    Next
    INDEX
    Explanations

    Information and facts

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '↵↵↵
    -0.07
     blot
    -0.07
    Pts
    -0.06
     ν
    -0.06
    ('$
    -0.06
    hua
    -0.06
    urnished
    -0.06
    Lou
    -0.06
     т
    -0.06
    _Res
    -0.06
    POSITIVE LOGITS
    olocation
    0.07
     appet
    0.07
    caller
    0.07
     dorm
    0.06
     방
    0.06
    Heading
    0.06
     společnosti
    0.06
    방
    0.06
    %p
    0.06
    _plain
    0.06
    Activations Density 0.022%

    No Known Activations