© 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. 109836
    Prev
    Next
    INDEX
    Explanations

    problem solving

    np_max-act · gemini-2.0-flash

    The neuron responds to collaborative, solution‐oriented action words (e.g. “find,” “solution,” “work,” “together,” “understand”).

    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
    ek
    -0.07
    icates
    -0.07
     Zimmer
    -0.06
    atars
    -0.06
    gia
    -0.06
    ToJson
    -0.06
     놀
    -0.06
    _detection
    -0.06
    つぶ
    -0.06
    まれ
    -0.06
    POSITIVE LOGITS
    (program
    0.07
     relieve
    0.06
     دن
    0.06
    _accepted
    0.06
     surname
    0.06
     созда
    0.06
    !I
    0.06
    On
    0.06
    /display
    0.06
    GenericType
    0.06
    Activations Density 0.021%

    No Known Activations