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. 3-RESID-POST-AA
    6. 121984
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    giatan
    -0.07
     seismic
    -0.06
    _soft
    -0.06
    <li
    -0.06
    処
    -0.06
    summer
    -0.06
     emacs
    -0.06
     dll
    -0.06
    葡
    -0.06
     applicationWill
    -0.06
    POSITIVE LOGITS
    /,
    0.07
     Cannabis
    0.07
    /@
    0.07
    /|
    0.07
    .Zoom
    0.07
     gays
    0.07
    /+
    0.07
     Eva
    0.07
     Swim
    0.06
    .EMAIL
    0.06
    Activations Density 0.034%

    No Known Activations