Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99362
    Prev
    Next
    INDEX
    Explanations

    Checking

    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
    zap
    -0.07
     compliment
    -0.06
     سرمایه
    -0.06
     teil
    -0.06
    站在
    -0.06
     Licht
    -0.06
     acqu
    -0.06
     pacing
    -0.06
    ampion
    -0.06
    (dialog
    -0.06
    POSITIVE LOGITS
     ****************************************************************************
    0.06
    .decor
    0.06
    868
    0.06
        ↵    ↵    ↵
    0.06
     autour
    0.06
    ,$_
    0.06
    月
    0.06
    Load
    0.06
     Violet
    0.06
    .ic
    0.06
    Activations Density 0.030%

    No Known Activations