© 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. 85828
    Prev
    Next
    INDEX
    Explanations

    scientific research papers

    np_max-act · gemini-2.0-flash

    This neuron detects scientific terms referring to biological substances, such as names of proteins, cytokines, hormones, or trace elements.

    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
     barred
    -0.07
    ่ได
    -0.07
     мень
    -0.07
    ¨ط
    -0.07
    -ch
    -0.06
    Io
    -0.06
    .Payload
    -0.06
    ?"↵↵
    -0.06
     []
↵
↵
    -0.06
     incor
    -0.06
    POSITIVE LOGITS
     Stefan
    0.06
     López
    0.06
    _presence
    0.06
    fel
    0.06
    ™
    0.06
    esco
    0.06
    .members
    0.06
    (QtCore
    0.06
     зробити
    0.06
     cez
    0.06
    Activations Density 0.088%

    No Known Activations