© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68837
    Prev
    Next
    INDEX
    Explanations

    future tense

    np_max-act · gemini-2.0-flash

    The neuron detects the assistant’s first‐person offers or commitments (e.g. “I’ll …,” “I can …,” “help you,” “provide you with …”) indicating promises to assist.

    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
     dr
    -0.06
    limits
    -0.06
     Chronicles
    -0.06
     imperson
    -0.06
     دوست
    -0.06
     Tobias
    -0.06
     foods
    -0.06
     servings
    -0.06
     tern
    -0.06
     CGRectGet
    -0.06
    POSITIVE LOGITS
    :x
    0.07
    .rs
    0.06
    isnan
    0.06
     슬
    0.06
    ROUGH
    0.06
     иг
    0.06
     Franç
    0.06
     качества
    0.06
    .My
    0.06
    =list
    0.06
    Activations Density 0.029%

    No Known Activations