© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109813
    Prev
    Next
    INDEX
    Explanations

    Scientific study results

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of multi‐stage or specialized procedural techniques (e.g., “two‐stage approach,” “in situ retrograde laser fenestration”) in medical methods descriptions.

    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
    инок
    -0.07
    ”
    -0.06
    اله
    -0.06
    /session
    -0.06
    inis
    -0.06
     merged
    -0.06
     to
    -0.06
    Tuple
    -0.06
     order
    -0.06
     деле
    -0.06
    POSITIVE LOGITS
    .Azure
    0.07
     FALL
    0.07
    _PROC
    0.07
    BED
    0.07
     حافظ
    0.06
    àu
    0.06
     поч
    0.06
     бли
    0.06
     몰
    0.06
    DECLARE
    0.06
    Activations Density 0.078%

    No Known Activations