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. 16169
    Prev
    Next
    INDEX
    Explanations

    fit

    np_max-act · gemini-2.0-flash

    The neuron activates on any token containing the substring “fit.”

    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
     Nov
    -0.07
     flames
    -0.07
     aime
    -0.07
     září
    -0.07
    uke
    -0.07
    668
    -0.07
     bull
    -0.07
     sword
    -0.06
    Na
    -0.06
     yandan
    -0.06
    POSITIVE LOGITS
     fit
    0.15
    fit
    0.14
     Fit
    0.14
    FIT
    0.13
     fitting
    0.13
    Fit
    0.12
     fits
    0.12
     FIT
    0.11
     fittings
    0.10
    .fit
    0.10
    Activations Density 0.014%

    No Known Activations