© 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. 7172
    Prev
    Next
    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash

    The neuron detects the exponent part (e.g. “10^(–5)”, “10^(–4)”, etc.) in scientific‐notation numbers.

    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
    _d
    -0.07
    .Generic
    -0.07
     territor
    -0.07
     ed
    -0.06
    (gl
    -0.06
    /sidebar
    -0.06
     Ful
    -0.06
     uch
    -0.06
    follower
    -0.06
     FA
    -0.06
    POSITIVE LOGITS
    ioned
    0.07
    vim
    0.06
     rewrite
    0.06
    .define
    0.06
    metics
    0.06
     cemetery
    0.06
     "-"
    0.06
     _______,
    0.06
     Вики
    0.06
     nightly
    0.06
    Activations Density 0.007%

    No Known Activations