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. 86303
    Prev
    Next
    INDEX
    Explanations

    Legal cases

    np_max-act · gemini-2.0-flash

    This neuron fires on the reporter‐citation line numbers (the floating‐point page references like “4.6875,” “4.6328125,” etc.) in case header metadata.

    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
    beeld
    -0.07
     Bs
    -0.07
     حرفه
    -0.07
     Al
    -0.06
    _reaction
    -0.06
    ем
    -0.06
     vš
    -0.06
    eneration
    -0.06
     Mathematical
    -0.06
     pygame
    -0.06
    POSITIVE LOGITS
    ROWN
    0.07
     presup
    0.06
     funny
    0.06
     rubbing
    0.06
    Provid
    0.06
     cwd
    0.06
    :string
    0.06
    بان
    0.06
    肥
    0.06
    Mexico
    0.06
    Activations Density 0.001%

    No Known Activations