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. 84684
    Prev
    Next
    INDEX
    Explanations

    pain

    np_max-act · gemini-2.0-flash

    The neuron identifies mentions of “chest pain” (i.e. the symptom chest pain).

    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
    _virtual
    -0.07
     SearchResult
    -0.07
    омен
    -0.06
     当
    -0.06
    "—
    -0.06
     बदल
    -0.06
    _Device
    -0.06
     projector
    -0.06
     Bride
    -0.06
     yıldız
    -0.06
    POSITIVE LOGITS
    語
    0.07
     관심
    0.07
     gained
    0.07
    นาน
    0.06
     qualities
    0.06
     strengthen
    0.06
    �
    0.06
     PAC
    0.06
     tư
    0.06
    anie
    0.06
    Activations Density 0.003%

    No Known Activations