© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129816
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    This neuron fires on the quotation‐mark tokens that introduce string literals (e.g. the " in `"Even"` or `"Odd"`) in code examples.

    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
    ніх
    -0.07
    ัปดาห
    -0.07
    ategorical
    -0.06
    Liked
    -0.06
    _mix
    -0.06
     gay
    -0.06
    уд
    -0.06
     chute
    -0.06
    986
    -0.06
     logical
    -0.06
    POSITIVE LOGITS
    asin
    0.07
    ो।
    0.06
     consid
    0.06
    <I
    0.06
     Split
    0.06
    .');
    ↵
    0.06
    wie
    0.06
     Özel
    0.06
    (dAtA
    0.06
    )]↵
    0.06
    Activations Density 0.018%

    No Known Activations