© 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. 42566
    Prev
    Next
    INDEX
    Explanations

    forum/article continuation

    np_max-act · gemini-2.0-flash

    references to medications and personal experiences with mental health treatment.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron responds to first‐person possessive and related self‐reference terms (e.g. “my,” “both”).

    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
    Disposition
    -0.08
    _associ
    -0.07
    Networking
    -0.07
     rover
    -0.07
    cheme
    -0.07
     [#
    -0.07
     ü
    -0.06
     Rai
    -0.06
    keyup
    -0.06
     proceeded
    -0.06
    POSITIVE LOGITS
     jsonResponse
    0.06
     PAGE
    0.06
     نشده
    0.06
     Thường
    0.06
     має
    0.06
    /inc
    0.06
    .ParseException
    0.06
    ーマ
    0.06
     válido
    0.06
     Başkanı
    0.06
    Activations Density 0.058%

    No Known Activations