© 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. 73948
    Prev
    Next
    INDEX
    Explanations

    Lists

    np_max-act · gemini-2.0-flash

    lists of items or examples in a specific format.

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

    The neuron detects list‐request phrases in user queries—especially tokens like “list,” “actresses,” and “who” indicating “list of X who…” questions.

    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
    Elapsed
    -0.07
    )}}"
    -0.06
     Pam
    -0.06
    Bounding
    -0.06
    ]][
    -0.06
    ;")↵
    -0.06
    (manager
    -0.06
    	unset
    -0.06
    )null
    -0.06
    "],
    -0.06
    POSITIVE LOGITS
    @stop
    0.06
     Дон
    0.06
    Guardar
    0.06
    ático
    0.06
    ','.
    0.06
    yect
    0.06
    榜
    0.06
     sue
    0.06
     aktif
    0.06
     společ
    0.06
    Activations Density 0.054%

    No Known Activations