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. 130714
    Prev
    Next
    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash

    This neuron never activates (it doesn’t respond to any tokens).

    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
    registers
    -0.07
    すぐ
    -0.06
    Son
    -0.06
     outputs
    -0.06
    Franc
    -0.06
    (pwd
    -0.06
    кар
    -0.06
    expired
    -0.06
     beau
    -0.06
    Sit
    -0.06
    POSITIVE LOGITS
     кон
    0.07
     Definitely
    0.06
    、私
    0.06
     вули
    0.06
     patiently
    0.06
    inic
    0.06
    ें↵↵
    0.06
    ์ได
    0.06
    ималь
    0.06
    ؟↵
    0.06
    Activations Density 0.014%

    No Known Activations