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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 81204
    Prev
    Next
    INDEX
    Explanations

    Code tables/arrays

    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
     niche
    -0.06
    _SOFT
    -0.06
    恒
    -0.06
     Appro
    -0.06
     ander
    -0.06
    /U
    -0.06
     tension
    -0.06
    Du
    -0.06
     Tai
    -0.06
     anchors
    -0.06
    POSITIVE LOGITS
    )this
    0.07
    _grade
    0.07
    (setting
    0.07
    YELLOW
    0.06
    [parent
    0.06
    sandbox
    0.06
    aneous
    0.06
    ?:
    0.06
    Lane
    0.06
     Cute
    0.06
    Activations Density 0.010%

    No Known Activations