© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58809
    Prev
    Next
    INDEX
    Explanations

    music personnel lists

    np_max-act · gemini-2.0-flash

    album titles and associated musical content.

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

    This neuron detects section or subsection headings (like “Personnel,” “Production,” “Engineered by,” “References,” etc.) in the album article.

    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
    _texture
    -0.07
    ाण
    -0.07
     (%)
    -0.07
     Knife
    -0.06
     несп
    -0.06
    _es
    -0.06
    endi
    -0.06
    ー
    -0.06
     ztr
    -0.06
     než
    -0.06
    POSITIVE LOGITS
     traveler
    0.07
     SM
    0.06
     carg
    0.06
    .Σ
    0.06
    _URL
    0.06
    asm
    0.06
     detachment
    0.06
    .updated
    0.06
    ASM
    0.06
    .Av
    0.06
    Activations Density 0.003%

    No Known Activations