© 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. 126388
    Prev
    Next
    INDEX
    Explanations

    Instructions

    np_max-act · gemini-2.0-flash

    It detects the imperative “step” verbs (like Sign, Prepare, Choose, Train, Fine-tune, Deploy) that introduce instructions in setup or how-to guides.

    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
     will
    -0.08
     ValueError
    -0.08
     mů
    -0.08
     would
    -0.08
     We
    -0.07
     Ive
    -0.07
    leyici
    -0.07
     we
    -0.07
     возникает
    -0.07
    will
    -0.07
    POSITIVE LOGITS
    dg
    0.06
    ln
    0.06
    .slides
    0.06
     EVP
    0.06
    .gt
    0.06
    PTR
    0.06
    جر
    0.06
    .groupBox
    0.06
     기업
    0.05
    餐
    0.05
    Activations Density 0.427%

    No Known Activations