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. 15-RESID-POST-AA
    6. 80701
    Prev
    Next
    INDEX
    Explanations

    Yes

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ApiResponse
    -0.06
    (holder
    -0.06
     Critical
    -0.06
    .Views
    -0.06
    [tag
    -0.06
    .Room
    -0.06
     işç
    -0.06
    -ID
    -0.06
     towing
    -0.06
    adio
    -0.06
    POSITIVE LOGITS
    .Constraint
    0.08
     webinar
    0.07
    冊
    0.07
     Lam
    0.07
     اکتبر
    0.07
     docker
    0.07
     rand
    0.07
    урс
    0.06
     Lens
    0.06
     است
    0.06
    Activations Density 0.024%

    No Known Activations