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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 52127
    Prev
    Next
    INDEX
    Explanations

    app

    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
     glyphs
    -0.07
    venues
    -0.07
    315
    -0.07
     Consolid
    -0.07
    ocide
    -0.07
    Clone
    -0.06
     Deaths
    -0.06
    idian
    -0.06
     posix
    -0.06
    isti
    -0.06
    POSITIVE LOGITS
     App
    0.10
     app
    0.09
    -app
    0.08
    app
    0.08
     Becky
    0.07
    A
    0.07
     ab
    0.07
    .An
    0.07
     theoretically
    0.07
     append
    0.07
    Activations Density 0.017%

    No Known Activations