© 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. 90671
    Prev
    Next
    INDEX
    Explanations

    games

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on instructional phrases that assign a task to multiple participants—e.g. “the other two players each have to fill in.”

    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
    Profile
    -0.07
    व
    -0.07
    Bed
    -0.07
    edor
    -0.06
    root
    -0.06
    viar
    -0.06
    amente
    -0.06
    [s
    -0.06
     translator
    -0.06
     стал
    -0.06
    POSITIVE LOGITS
    jpeg
    0.06
    \">
    0.06
    ♠
    0.06
     Bene
    0.06
    Tahoma
    0.06
    _original
    0.06
    navbarSupportedContent
    0.06
    ubs
    0.06
     heals
    0.06
    ?]
    0.06
    Activations Density 0.002%

    No Known Activations