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. 11-RESID-POST-AA
    6. 81337
    Prev
    Next
    INDEX
    Explanations

    claim

    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
     oxygen
    -0.07
    middlewares
    -0.07
    @Enable
    -0.07
     GObject
    -0.07
     Oxygen
    -0.07
     Peace
    -0.07
    .tabPage
    -0.07
    Apart
    -0.07
     Essex
    -0.06
    iễ
    -0.06
    POSITIVE LOGITS
     claim
    0.09
     claims
    0.09
     Claims
    0.09
     Claim
    0.08
    eline
    0.07
     FL
    0.07
    ил
    0.07
    ler
    0.07
    드
    0.07
    $
    0.07
    Activations Density 0.008%

    No Known Activations