© 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. 76354
    Prev
    Next
    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash

    The neuron specifically lights up on the backslash tokens that introduce LaTeX/math‐mode commands (e.g. “\”).

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

    statements involving research methodologies and their evaluation.

    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
     bicycles
    -0.07
     sĩ
    -0.06
    Houston
    -0.06
    (Messages
    -0.06
     Devil
    -0.06
     jí
    -0.06
     ва
    -0.06
     Cup
    -0.06
     IsNot
    -0.06
    شی
    -0.06
    POSITIVE LOGITS
     -$
    0.07
     ='
    0.07
     ="
    0.07
    BT
    0.06
     ={↵
    0.06
    342
    0.06
     bm
    0.06
     //(
    0.06
     �
    0.06
    激
    0.06
    Activations Density 0.343%

    No Known Activations