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. 86026
    Prev
    Next
    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the word “file,” especially in license‐header comments.

    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
     Briggs
    -0.07
    critical
    -0.07
    )،
    -0.06
    /top
    -0.06
     Netanyahu
    -0.06
    scheme
    -0.06
     Bilim
    -0.06
    _norm
    -0.06
    ifact
    -0.06
    avier
    -0.06
    POSITIVE LOGITS
    (['/
    0.07
     across
    0.06
    	Error
    0.06
     boxer
    0.06
     Inn
    0.06
    .chk
    0.06
     мяг
    0.06
    але
    0.06
    _GU
    0.06
    uncture
    0.06
    Activations Density 0.000%

    No Known Activations