© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 722
    Prev
    Next
    INDEX
    Explanations

    normal or negative

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of normal diagnostic findings (e.g. “normal” in the context of medical imaging or test results).

    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
     измер
    -0.06
     Sağ
    -0.06
     Mum
    -0.06
    Map
    -0.06
     Beyond
    -0.06
    =no
    -0.06
    .styleable
    -0.06
    рип
    -0.06
     embraced
    -0.06
    _dyn
    -0.06
    POSITIVE LOGITS
    erie
    0.06
     XML
    0.06
    istent
    0.06
     comment
    0.06
    Exact
    0.06
    ',"
    0.06
     "!
    0.06
     av
    0.06
    .divide
    0.06
    /images
    0.06
    Activations Density 0.026%

    No Known Activations