© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 118758
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of peroxisome-related biological concepts (references to peroxisomes or peroxisomal topics).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Babies
    -0.07
    .width
    -0.07
    (List
    -0.07
    _tr
    -0.06
    _success
    -0.06
    imax
    -0.06
    ович
    -0.06
    -best
    -0.06
    严
    -0.06
    _No
    -0.06
    POSITIVE LOGITS
     climbed
    0.06
     sustainability
    0.06
     mercury
    0.06
     Transformer
    0.06
     Jeep
    0.06
    
    0.06
     следует
    0.06
     mí
    0.06
    .isPresent
    0.06
     guessing
    0.06
    Activations Density 0.001%

    No Known Activations