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. 40386
    Prev
    Next
    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash

    The neuron activates on the leading asterisk tokens in multi‐line comment blocks (the “*” at the start of each comment line).

    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
    NSSet
    -0.07
    جع
    -0.07
    wake
    -0.06
    _ts
    -0.06
    abaj
    -0.06
    itable
    -0.06
     свер
    -0.06
     �
    -0.06
    -eyed
    -0.06
    atement
    -0.06
    POSITIVE LOGITS
    .hxx
    0.08
    aina
    0.07
    (Config
    0.07
    ổng
    0.06
    )};↵
    0.06
     applaud
    0.06
    =headers
    0.06
     target
    0.06
     Dayton
    0.06
     PRIVATE
    0.06
    Activations Density 0.005%

    No Known Activations