© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91232
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron fires on in-line punctuation (especially commas) and the following small function words (e.g. “and,” “thus”) that introduce subordinate or parenthetical clauses.

    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
    ypi
    -0.07
    �
    -0.06
    Has
    -0.06
    hint
    -0.06
    ignant
    -0.06
    GTK
    -0.06
    ember
    -0.06
     Lazar
    -0.06
    Sale
    -0.06
    :↵↵↵↵
    -0.06
    POSITIVE LOGITS
    _needed
    0.07
    evaluate
    0.06
    那么
    0.06
    >'+↵
    0.06
     siyas
    0.06
     model
    0.06
    _coordinate
    0.06
     Avrupa
    0.06
     fundraiser
    0.06
     probes
    0.06
    Activations Density 0.000%

    No Known Activations