© 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. 11-RESID-POST-AA
    11. 12461
    Prev
    Next
    INDEX
    Explanations

    mechanical/technical components

    np_max-act · gemini-2.0-flash

    technical terms related to engineering and mechanical designs.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on mentions of filter components or modules (e.g. “filter,” “filter assembly,” “filter rods,” etc.) in a technical description.

    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
    LEM
    -0.08
    .end
    -0.07
     diary
    -0.06
     convenient
    -0.06
    _blue
    -0.06
     Kernel
    -0.06
    wine
    -0.06
    Selected
    -0.06
    oined
    -0.06
    editor
    -0.06
    POSITIVE LOGITS
     fiz
    0.08
    .utilities
    0.07
     toi
    0.07
    (sqrt
    0.07
     क
    0.06
     ging
    0.06
     singer
    0.06
    ności
    0.06
    /input
    0.06
    .son
    0.06
    Activations Density 0.075%

    No Known Activations