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. 130415
    Prev
    Next
    INDEX
    Explanations

    small

    np_max-act · gemini-2.0-flash

    This neuron responds to words that express small size or quantity (e.g., small, bit, fine, amount).

    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
     zar
    -0.06
     стол
    -0.06
    蒙
    -0.06
    ellig
    -0.06
     له
    -0.06
    _vertex
    -0.06
     oppressive
    -0.06
    arious
    -0.06
    ocolate
    -0.06
     亚洲
    -0.06
    POSITIVE LOGITS
    (__
    0.06
    (total
    0.06
    .String
    0.06
     smaller
    0.06
    ((__
    0.06
     Claim
    0.06
    ‌ن
    0.06
     hiss
    0.06
     Challenger
    0.06
     Beef
    0.06
    Activations Density 0.007%

    No Known Activations