Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 84679
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens (digits and numbers) embedded in mathematical expressions.

    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
    549
    -0.07
    _gem
    -0.07
     Ore
    -0.07
    token
    -0.06
    กราคม
    -0.06
     �
    -0.06
     snippet
    -0.06
    occ
    -0.06
    ANCED
    -0.06
    ené
    -0.06
    POSITIVE LOGITS
     покры
    0.07
     rele
    0.06
     difference
    0.06
     '",
    0.06
     Difference
    0.06
     NH
    0.06
     divorce
    0.06
     нали
    0.06
     Suppose
    0.06
     equival
    0.06
    Activations Density 0.017%

    No Known Activations