© 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. 55904
    Prev
    Next
    INDEX
    Explanations

    reel

    np_max-act · gemini-2.0-flash

    technical terms related to mechanical and electrical devices.

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

    The neuron detects mentions of spool‐ or reel‐based winding (take‐up) mechanisms.

    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
    ords
    -0.07
    裏
    -0.06
    لاة
    -0.06
     purple
    -0.06
    paramref
    -0.06
     Hazel
    -0.06
    あげ
    -0.06
     currency
    -0.06
    du
    -0.06
    dition
    -0.06
    POSITIVE LOGITS
    rottle
    0.07
     cortical
    0.07
     ταιν
    0.07
    İTESİ
    0.06
    iglia
    0.06
     Pine
    0.06
     {|
    0.06
    imonials
    0.06
    (existing
    0.06
     استان
    0.06
    Activations Density 0.007%

    No Known Activations