© 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. 15-RESID-POST-AA
    6. 115892
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    Finds commas and nearby function words that mark clause boundaries (i.e., punctuation separating clauses).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    úmer
    -0.06
    ocache
    -0.06
    Cake
    -0.06
     forwarded
    -0.06
     Infinite
    -0.06
    .AspNet
    -0.06
    -sidebar
    -0.06
    909
    -0.06
     carries
    -0.06
    finite
    -0.06
    POSITIVE LOGITS
    си
    0.07
    .ir
    0.07
     Positioned
    0.07
     experimented
    0.07
     pek
    0.06
     Jub
    0.06
    (seq
    0.06
    (bean
    0.06
    klä
    0.06
     Volvo
    0.06
    Activations Density 0.001%

    No Known Activations