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. 15-RESID-POST-AA
    6. 21636
    Prev
    Next
    INDEX
    Explanations

    medication

    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
    'L
    -0.06
     Toll
    -0.06
     SELECT
    -0.06
    м
    -0.06
     simult
    -0.06
     sandwich
    -0.06
    AtIndex
    -0.06
    [state
    -0.06
    (SELECT
    -0.06
     instantaneous
    -0.06
    POSITIVE LOGITS
     Charset
    0.06
     개
    0.06
     Stellar
    0.06
     растения
    0.06
    opacity
    0.06
    akedown
    0.06
     رفته
    0.06
     signup
    0.06
    oracle
    0.06
    romium
    0.06
    Activations Density 0.024%

    No Known Activations