© 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. 128634
    Prev
    Next
    INDEX
    Explanations

    questions and technical documents

    np_max-act · gemini-2.0-flash

    The neuron detects requests for vivid, sensory‐oriented descriptions of physical feelings (e.g. “what it would feel like…” in tactile language).

    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
     Particularly
    -0.07
    309
    -0.07
    .tt
    -0.07
    _can
    -0.07
     university
    -0.06
     acceleration
    -0.06
    ick
    -0.06
     CDDL
    -0.06
    prisingly
    -0.06
    -No
    -0.06
    POSITIVE LOGITS
    ./(
    0.06
     获取
    0.06
     احتم
    0.06
    تم
    0.06
    [jj
    0.06
    isini
    0.06
    *b
    0.06
    [tmp
    0.06
     öt
    0.06
     ऊ
    0.06
    Activations Density 0.093%

    No Known Activations