© 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. 7595
    Prev
    Next
    INDEX
    Explanations

    (-

    np_max-act · gemini-2.0-flash

    The neuron never fires on any of these purely mathematical/formula‐heavy passages – it appears to be inactive (i.e. it does not detect any pattern) in this context.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    mathematical expressions and equations involving variables and derivatives.

    oai_token-act-pair · gpt-4o-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
    _place
    -0.07
    integral
    -0.06
     Whereas
    -0.06
     Roll
    -0.06
    —he
    -0.06
     OVERRIDE
    -0.06
     IMO
    -0.06
     disadvantage
    -0.06
     locus
    -0.06
     approaches
    -0.06
    POSITIVE LOGITS
    	video
    0.06
     mies
    0.06
     roofs
    0.06
     μην
    0.06
    _expired
    0.06
     Definition
    0.06
    .sale
    0.06
    <GameObject
    0.06
     nejd
    0.06
    atura
    0.06
    Activations Density 0.003%

    No Known Activations