© 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. 5942
    Prev
    Next
    INDEX
    Explanations

    questions and requests for help

    np_max-act · gemini-2.0-flash

    The neuron detects user-issued proofreading or correction requests phrased as imperatives (e.g. “please fix,” “proofread and correct”).

    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
     productions
    -0.06
    Back
    -0.06
    zim
    -0.06
    alar
    -0.06
    acked
    -0.06
    quests
    -0.06
    .StylePriority
    -0.06
    ormsg
    -0.06
     confession
    -0.06
     born
    -0.06
    POSITIVE LOGITS
     Bü
    0.07
    /n
    0.07
    _operand
    0.06
    ğitim
    0.06
     Dispose
    0.06
     richest
    0.06
    (Content
    0.06
     گروه
    0.06
    @Module
    0.06
     MEP
    0.06
    Activations Density 0.044%

    No Known Activations