© 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. 57962
    Prev
    Next
    INDEX
    Explanations

    heat

    np_max-act · gemini-2.0-flash

    The neuron fires on phrases describing heating or preheating steps—especially mentions of heat, temperature settings, and getting a cooking surface or oven up to temperature.

    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
     branches
    -0.07
    ملكة
    -0.06
    _frame
    -0.06
    datatype
    -0.06
     shadows
    -0.06
    .pixel
    -0.06
    =nil
    -0.06
     hel
    -0.06
    -filter
    -0.06
    .gif
    -0.06
    POSITIVE LOGITS
     prolonged
    0.07
     Không
    0.07
    .С
    0.07
    818
    0.06
    _wrong
    0.06
     Nhà
    0.06
    ař
    0.06
    šlo
    0.06
     imped
    0.06
     socio
    0.06
    Activations Density 0.009%

    No Known Activations