© 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. 129727
    Prev
    Next
    INDEX
    Explanations

    biology and medicine

    np_max-act · gemini-2.0-flash

    The neuron selectively responds to very short standalone tokens—single letters or two-character strings (often digits or abbreviations) used as technical codes.

    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
    พล
    -0.07
    remote
    -0.07
    UFFIX
    -0.06
    range
    -0.06
    인
    -0.06
    -series
    -0.06
    427
    -0.06
     trop
    -0.06
    -country
    -0.06
    Trim
    -0.06
    POSITIVE LOGITS
    िसक
    0.07
     peru
    0.07
    -equipped
    0.07
    deer
    0.06
    опрос
    0.06
    ulus
    0.06
    SS
    0.06
    <Cell
    0.06
    expects
    0.06
    Ģ
    0.06
    Activations Density 0.432%

    No Known Activations