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. 23-RESID-POST-AA
    6. 40624
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upos
    -0.07
    Translation
    -0.07
     C
    -0.06
     PDF
    -0.06
    utilities
    -0.06
     harmony
    -0.06
     NUITKA
    -0.06
     Г
    -0.06
    annual
    -0.06
    125
    -0.06
    POSITIVE LOGITS
    _concat
    0.06
    异常
    0.06
    pleted
    0.06
    ]},↵
    0.06
     अपन
    0.06
    ;x
    0.06
    ournemouth
    0.06
     incididunt
    0.06
    Ơ
    0.06
     [<
    0.06
    Activations Density 0.179%

    No Known Activations