© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13024
    Prev
    Next
    INDEX
    Explanations

    scientific/medical procedures

    np_max-act · gemini-2.0-flash

    The neuron flags technical method‐and‐process terms (often passive‐voice procedure verbs and related action words) in scientific or experimental text.

    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
    _fail
    -0.07
     revoked
    -0.06
    .servers
    -0.06
     addCriterion
    -0.06
    vided
    -0.06
    _mesh
    -0.06
     Tai
    -0.06
    _heat
    -0.06
     traumatic
    -0.06
    _repo
    -0.06
    POSITIVE LOGITS
     obvious
    0.06
    flies
    0.06
     trai
    0.06
    .fileName
    0.06
     ऑनल
    0.06
     promising
    0.06
    eleri
    0.06
     unfortunate
    0.06
    -goal
    0.06
    ……………………
    0.06
    Activations Density 0.077%

    No Known Activations