Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 5506
    Prev
    Next
    INDEX
    Explanations

    emphasis

    np_max-act · gemini-2.0-flash

    Financial report / earnings-related content — section headings, numeric metrics and terms from corporate earnings and financial summaries (revenues, EPS, growth percentages, margins, transactions).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .↵
    -0.06
     vile
    -0.06
    ِر
    -0.06
    .↵↵
    -0.06
    inosaur
    -0.06
     yielding
    -0.06
     vh
    -0.06
     Ελλάδα
    -0.06
    ."↵
    -0.06
    χρι
    -0.06
    POSITIVE LOGITS
     ileri
    0.08
    _MACHINE
    0.06
     služeb
    0.06
     rolling
    0.06
     послуг
    0.06
    holm
    0.06
    領
    0.06
    .setColor
    0.06
    Rated
    0.06
     bày
    0.06
    Activations Density 37.577%

    No Known Activations