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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 91239
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on syntax‐rule token names in grammar definitions (e.g. “comment,” “string,” “escape,” “line,” 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
    DidChange
    -0.07
     receptive
    -0.07
     τα
    -0.06
     truyền
    -0.06
     Ruf
    -0.06
    +'.
    -0.06
    Seven
    -0.06
    -types
    -0.06
     Kate
    -0.06
    练
    -0.06
    POSITIVE LOGITS
    tle
    0.07
    _Store
    0.06
    ativity
    0.06
     einf
    0.06
    sar
    0.06
    .vaadin
    0.06
    ied
    0.06
    雅
    0.06
    Up
    0.06
    /gen
    0.06
    Activations Density 0.008%

    No Known Activations