© 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. 90820
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron is looking for function or method declaration signatures (e.g. the “def” keyword and its parameter/type list).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    text that describes programming concepts and patterns in code, particularly related to abstract layers and interfaces.

    oai_token-act-pair · gpt-4o-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
     위치
    -0.06
    .BatchNorm
    -0.06
     μέρος
    -0.06
    ografie
    -0.06
    .IsMatch
    -0.06
    ffen
    -0.06
     původ
    -0.06
    :_
    -0.06
    azo
    -0.06
     Pickup
    -0.06
    POSITIVE LOGITS
     Ships
    0.07
    dal
    0.06
    .AlertDialog
    0.06
     Broadway
    0.06
    GU
    0.06
     searching
    0.06
    491
    0.06
    演
    0.06
    ตล
    0.06
    dress
    0.06
    Activations Density 0.007%

    No Known Activations