© 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. 59397
    Prev
    Next
    INDEX
    Explanations

    won

    np_max-act · gemini-2.0-flash

    This neuron doesn’t pick out any clear linguistic category but instead sporadically lights up on low-frequency or otherwise atypical tokens.

    oai_token-act-pair · o4-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
     sc
    -0.07
    isté
    -0.06
    .un
    -0.06
     undergone
    -0.06
    but
    -0.06
     commenter
    -0.06
    hou
    -0.06
     notify
    -0.06
    ended
    -0.06
    sp
    -0.06
    POSITIVE LOGITS
    恒
    0.07
    維
    0.07
     مناس
    0.06
    訓
    0.06
     غذ
    0.06
     مي
    0.06
    装置
    0.06
     Telecom
    0.06
    Buy
    0.06
    _SYM
    0.06
    Activations Density 0.000%

    No Known Activations