© 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. 39169
    Prev
    Next
    INDEX
    Explanations

    hear

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of human sensory modalities (e.g., seeing, hearing, touching, tasting, smelling).

    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
    unexpected
    -0.07
     GetEnumerator
    -0.07
    -dashboard
    -0.07
    avaş
    -0.06
    lags
    -0.06
    .INFO
    -0.06
     fil
    -0.06
    bx
    -0.06
    _BOUNDS
    -0.06
    stud
    -0.06
    POSITIVE LOGITS
     появ
    0.07
    EEDED
    0.07
    очка
    0.06
     très
    0.06
    енню
    0.06
    سی
    0.06
     hg
    0.06
    ンブ
    0.06
    UpInside
    0.06
    Captain
    0.06
    Activations Density 0.015%

    No Known Activations