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. 40563
    Prev
    Next
    INDEX
    Explanations

    Back

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of clock “hands” (in particular the “hour” and “minute” hand).

    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
     Plugin
    -0.06
     rac
    -0.06
     Trojan
    -0.06
    util
    -0.06
    clusters
    -0.06
     Arch
    -0.06
     Proud
    -0.06
    List
    -0.06
    translator
    -0.06
    ố
    -0.06
    POSITIVE LOGITS
    RIORITY
    0.07
    (renderer
    0.06
    마다
    0.06
    :v
    0.06
     rage
    0.06
    've
    0.06
     sermon
    0.06
    ヾ
    0.06
     btc
    0.06
     coward
    0.06
    Activations Density 0.134%

    No Known Activations