© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 129598
    Prev
    Next
    INDEX
    Explanations

    university

    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
    iphy
    -0.06
     Plains
    -0.06
    master
    -0.06
    <lemma
    -0.06
     RULE
    -0.06
     studi
    -0.06
     Snyder
    -0.06
    REW
    -0.06
    elp
    -0.06
     wives
    -0.06
    POSITIVE LOGITS
    涉
    0.07
     示
    0.07
    按
    0.06
     ε
    0.06
    uo
    0.06
    _crop
    0.06
     sneak
    0.06
     отдел
    0.06
    巨
    0.06
    .surname
    0.06
    Activations Density 0.060%

    No Known Activations