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. 22000
    Prev
    Next
    INDEX
    Explanations

    equals sign

    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
    etadata
    -0.07
    _master
    -0.06
    indicator
    -0.06
     blk
    -0.06
     hmac
    -0.06
    THREAD
    -0.06
     AM
    -0.06
    eworthy
    -0.06
    failure
    -0.06
     births
    -0.06
    POSITIVE LOGITS
     insanlar
    0.07
    .AddColumn
    0.07
    -L
    0.07
     thé
    0.07
    ,'#
    0.07
    +='
    0.06
     Elev
    0.06
    ::/
    0.06
     професій
    0.06
    -resolution
    0.06
    Activations Density 0.001%

    No Known Activations