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. 86083
    Prev
    Next
    INDEX
    Explanations

    solar and wind

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of renewable‐energy projects, especially “solar farm” or “wind farm” and related capacity/power terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     uk
    -0.07
     safe
    -0.07
     Rosen
    -0.06
     explorer
    -0.06
    asley
    -0.06
     peanut
    -0.06
     TOO
    -0.06
    _strategy
    -0.06
    .Match
    -0.06
     ise
    -0.06
    POSITIVE LOGITS
    (EFFECT
    0.06
     residences
    0.06
    -----------
    0.06
    ---
    0.06
    گوی
    0.06
    ="__
    0.06
    istas
    0.06
     Caesar
    0.06
    /entity
    0.06
    -columns
    0.06
    Activations Density 0.011%

    No Known Activations