© 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. 90855
    Prev
    Next
    INDEX
    Explanations

    "many a" idiomatic language

    np_max-act · gemini-2.0-flash

    text related to historical figures and their contributions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects archaic or poetic first‐person expressions—particularly inverted phrases beginning with adverbs (e.g. “Often have I …,” “Many’s a time …”).

    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
    au
    -0.06
     Nova
    -0.06
     해
    -0.06
     Renewable
    -0.06
     lag
    -0.06
    076
    -0.06
    植
    -0.06
     SG
    -0.06
    ushman
    -0.06
     Low
    -0.06
    POSITIVE LOGITS
    .Many
    0.07
     Toastr
    0.07
     cube
    0.07
     heartbreaking
    0.06
    .priv
    0.06
     glo
    0.06
    TRUE
    0.06
     Rebels
    0.06
    oslav
    0.06
    Bs
    0.06
    Activations Density 0.052%

    No Known Activations