© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 47989
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting floating-point numeric literals (tokens containing a decimal point and fractional digits).

    oai_token-act-pair · o4-mini
    Triggered by @xinyanhu8

    code related to OpenGL and graphics rendering, specifically shader programming and vertex management.

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    cnt
    -0.07
    وط
    -0.07
     optimism
    -0.06
    Count
    -0.06
    树
    -0.06
    ijk
    -0.06
    strar
    -0.06
    ogan
    -0.06
    utta
    -0.06
     Taxes
    -0.06
    POSITIVE LOGITS
     ホ
    0.06
     ELECT
    0.06
    .CON
    0.06
     NOR
    0.06
    _AUDIO
    0.06
    Transition
    0.06
     출연
    0.06
     FRONT
    0.06
    authentication
    0.06
     tend
    0.06
    Activations Density 0.021%

    No Known Activations