© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 43342
    Prev
    Next
    INDEX
    Explanations

    citations

    np_max-act · gemini-2.0-flash

    terms related to metabolic and dietary health issues.

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

    The neuron primarily detects in‐text citation markers (e.g. backslash-delimited reference numbers and bracketed citation tags).

    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
    apyrus
    -0.07
    寺
    -0.07
     membranes
    -0.06
    intree
    -0.06
    γγ
    -0.06
    )"
    -0.06
    Women
    -0.06
     kube
    -0.06
    iggins
    -0.06
    ής
    -0.06
    POSITIVE LOGITS
    /g
    0.06
     paced
    0.06
    ์ล
    0.06
    classNames
    0.06
     itemView
    0.06
    OPY
    0.06
     第
    0.06
    (path
    0.06
     Meta
    0.06
     Lux
    0.06
    Activations Density 0.019%

    No Known Activations