© 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. 68818
    Prev
    Next
    INDEX
    Explanations

    people

    np_max-act · gemini-2.0-flash

    The neuron activates on words referring to people (e.g. “others,” “people,” “you,” “someone”), flagging mentions of persons or interpersonal references.

    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
    できる
    -0.06
    이었다
    -0.06
    を使
    -0.06
     toaster
    -0.06
    															
    -0.06
     такое
    -0.06
    ują
    -0.06
    scenario
    -0.06
     несколь
    -0.06
    _COLOR
    -0.06
    POSITIVE LOGITS
    _;↵
    0.06
    .mm
    0.06
    [jj
    0.06
     correl
    0.06
    .mass
    0.06
     ned
    0.06
    Dam
    0.06
    org
    0.06
     PSG
    0.06
    .minLength
    0.06
    Activations Density 0.052%

    No Known Activations