© 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. 55757
    Prev
    Next
    INDEX
    Explanations

    programming languages

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on words and phrases emphasizing ease of use or learn-ability—e.g. “easy,” “learn,” “simple,” “straightforward.”

    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
    flat
    -0.07
     거의
    -0.07
     hafta
    -0.06
    Haz
    -0.06
     قسمت
    -0.06
    仔
    -0.06
    .eql
    -0.06
    nect
    -0.06
    不知
    -0.06
    _now
    -0.06
    POSITIVE LOGITS
    :init
    0.07
    ImplOptions
    0.07
    /community
    0.07
    Ệ
    0.06
    childs
    0.06
    /plain
    0.06
    -mediated
    0.06
    麦
    0.06
    министра
    0.06
    ITHUB
    0.06
    Activations Density 0.019%

    No Known Activations