© 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. 109850
    Prev
    Next
    INDEX
    Explanations

    Conversational speech

    np_max-act · gemini-2.0-flash

    The neuron fires on words where the speaker is directly expressing or asking about their own feelings, experiences, or emotional challenges.

    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
    _Arg
    -0.06
    oice
    -0.06
    771
    -0.06
     boob
    -0.06
    af
    -0.06
     چیز
    -0.06
    écial
    -0.06
    Wake
    -0.06
    PerPixel
    -0.06
     panoramic
    -0.06
    POSITIVE LOGITS
    .assertTrue
    0.07
     CID
    0.07
    -check
    0.06
     Eid
    0.06
     crawl
    0.06
    MenuItem
    0.06
     irre
    0.06
     [*
    0.06
    =F
    0.06
    ,i
    0.06
    Activations Density 0.026%

    No Known Activations