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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 104425
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
     captive
    -0.07
     Werner
    -0.07
     anunci
    -0.06
     Kane
    -0.06
     это
    -0.06
    Explorer
    -0.06
    しても
    -0.06
    ccount
    -0.06
    DEN
    -0.06
    account
    -0.06
    POSITIVE LOGITS
     Григор
    0.07
    iar
    0.07
     removable
    0.07
     â
    0.06
     Би
    0.06
    $MESS
    0.06
     game
    0.06
     orm
    0.06
     수강
    0.06
     rootReducer
    0.06
    Activations Density 0.000%

    No Known Activations