© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58760
    Prev
    Next
    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash

    The neuron detects arithmetic‐operation cue words and phrases (e.g. add, subtract, sum, difference, distance, calculate, put together).

    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
    dfs
    -0.07
    _erase
    -0.07
    хів
    -0.07
    getManager
    -0.06
    ประก
    -0.06
    _TOP
    -0.06
    Cancelled
    -0.06
    KeyValuePair
    -0.06
    =output
    -0.06
    .middle
    -0.06
    POSITIVE LOGITS
     Anna
    0.07
    Force
    0.07
     Julie
    0.07
     rho
    0.06
    self
    0.06
     DE
    0.06
    weather
    0.06
    orth
    0.06
    studio
    0.06
     NST
    0.06
    Activations Density 0.001%

    No Known Activations