© 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. 15-RESID-POST-AA
    11. 22605
    Prev
    Next
    INDEX
    Explanations

    Online dialogue

    np_max-act · gemini-2.0-flash

    It detects dialogue and speech-related tokens—quotation marks, speech/utterance verbs and the short action/response words that appear around lines of spoken dialogue.

    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
    질
    -0.07
    iang
    -0.07
    allocator
    -0.07
     affirm
    -0.07
    _v
    -0.06
    dız
    -0.06
    영상
    -0.06
    (render
    -0.06
    ecture
    -0.06
     Guill
    -0.06
    POSITIVE LOGITS
    ¦
    0.07
     můžete
    0.07
    .AddModelError
    0.07
     AssemblyTitle
    0.06
     بیش
    0.06
     cấp
    0.06
    ,},↵
    0.06
    .Top
    0.06
    .Substring
    0.06
     sebep
    0.06
    Activations Density 0.026%

    No Known Activations