© 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. 55564
    Prev
    Next
    INDEX
    Explanations

    Reduc

    np_max-act · gemini-2.0-flash

    The neuron detects the tokenized root for reduction/decrease (the "Reduc" token), especially when it appears as a heading or title at the start of a document.

    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
     mús
    -0.07
     SharedModule
    -0.07
    '>";↵
    -0.07
    ():↵
    -0.06
    .rnn
    -0.06
    >;↵↵
    -0.06
    -run
    -0.06
    .:.:.:.:.:.:.:.:.:.:.:.:.:.:.:.:
    -0.06
    ponsive
    -0.06
     ~>
    -0.06
    POSITIVE LOGITS
    .Pass
    0.07
    oseconds
    0.06
    -element
    0.06
     Falls
    0.06
    _bits
    0.06
    (timer
    0.06
    tl
    0.06
    -cont
    0.06
     kart
    0.06
     IMD
    0.06
    Activations Density 0.123%

    No Known Activations