© 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. 39068
    Prev
    Next
    INDEX
    Explanations

    defense

    np_max-act · gemini-2.0-flash

    references to military personnel involved in historical sieges.

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

    The neuron selectively activates on French words (i.e. tokens in the French language).

    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
     special
    -0.07
     sincerity
    -0.07
     commune
    -0.06
     auction
    -0.06
     iff
    -0.06
    ulfilled
    -0.06
     díl
    -0.06
     pop
    -0.06
     SPECIAL
    -0.06
    _EXTENSION
    -0.06
    POSITIVE LOGITS
    Cong
    0.07
    .“
    0.06
    اکی
    0.06
    _ec
    0.06
     MSI
    0.06
     impover
    0.06
     нерв
    0.06
    _mob
    0.06
    !“
    0.06
    ợi
    0.06
    Activations Density 0.016%

    No Known Activations