© 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. 57583
    Prev
    Next
    INDEX
    Explanations

    Math/Logic Questions

    np_max-act · gemini-2.0-flash

    This neuron responds to single‐letter mathematical identifiers (like A, B, C, D) appearing in formal math expressions.

    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
    ELSE
    -0.07
    ooter
    -0.07
    antar
    -0.06
    ropic
    -0.06
    average
    -0.06
     materials
    -0.06
    енную
    -0.06
     going
    -0.06
     layered
    -0.06
    ить
    -0.06
    POSITIVE LOGITS
     Fs
    0.06
    ��
    0.06
     IQ
    0.06
    compan
    0.06
    ?',
    0.06
    (stmt
    0.06
    ύν
    0.06
     sonucunda
    0.06
    .operations
    0.06
    ;"><?
    0.06
    Activations Density 0.024%

    No Known Activations