© 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. 59159
    Prev
    Next
    INDEX
    Explanations

    access

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of multiple‐access or multiplexing schemes (e.g. terms like “Multiple Access,” FDMA, TDMA, CDMA, OFDMA, SC-FDMA, etc.).

    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
     consulting
    -0.07
     VS
    -0.07
    bruar
    -0.07
    .FILES
    -0.06
    амп
    -0.06
     Wellness
    -0.06
    律宾
    -0.06
    علوم
    -0.06
     NV
    -0.06
     Gulf
    -0.06
    POSITIVE LOGITS
    upakan
    0.07
     consenting
    0.07
    .entrySet
    0.07
     wrest
    0.06
    smarty
    0.06
     modelo
    0.06
    invitation
    0.06
     entrar
    0.06
    women
    0.06
     bev
    0.06
    Activations Density 0.002%

    No Known Activations