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. 22578
    Prev
    Next
    INDEX
    Explanations

    code

    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
    declare
    -0.06
    암
    -0.06
    策
    -0.06
     Marion
    -0.06
     Flesh
    -0.06
    amacare
    -0.06
     rule
    -0.06
    ν
    -0.06
    Iron
    -0.06
    MMMM
    -0.06
    POSITIVE LOGITS
    はない
    0.08
     eğit
    0.07
    十一
    0.06
    .path
    0.06
    aş
    0.06
     laisse
    0.06
     cider
    0.06
     ortak
    0.06
    $string
    0.06
    .CreateDirectory
    0.06
    Activations Density 0.024%

    No Known Activations