© 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. 129614
    Prev
    Next
    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on the conditional “if,” i.e. it’s detecting the word “if” in the text.

    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
     Gratis
    -0.06
     جهان
    -0.06
    、中
    -0.06
     quote
    -0.06
    aleur
    -0.06
    ails
    -0.06
    الس
    -0.06
    _ctxt
    -0.06
    ๒
    -0.06
    RefCount
    -0.06
    POSITIVE LOGITS
     kv
    0.07
    íf
    0.07
    원
    0.07
    Kal
    0.06
     evidenced
    0.06
     userService
    0.06
     SPL
    0.06
     webpack
    0.06
    kt
    0.06
    ?>↵↵↵
    0.06
    Activations Density 0.008%

    No Known Activations