© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125141
    Prev
    Next
    INDEX
    Explanations

    ytic

    np_max-act · gemini-2.0-flash

    The neuron fires on technical terms referring to an enzyme’s catalytic or active‐site region (e.g. “catalytic,” “site,” “domain,” “flap subdomain,” “allosteric”).

    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
    Minor
    -0.07
    .white
    -0.07
    Pale
    -0.07
    　ゝ
    -0.06
    anche
    -0.06
     ordinal
    -0.06
    aldo
    -0.06
    нист
    -0.06
     locus
    -0.06
     organize
    -0.06
    POSITIVE LOGITS
     앉
    0.07
    /screen
    0.06
     tableau
    0.06
     sug
    0.06
     gł
    0.06
    огра
    0.06
    -array
    0.06
    _keywords
    0.06
    -reg
    0.06
    .getEmail
    0.06
    Activations Density 0.006%

    No Known Activations