© 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. 7-RESID-POST-AA
    11. 5506
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    tokens that are digits or small numeric sequences (track numbers, years, times, and numbers in parentheses).

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     operational
    -0.07
     Windows
    -0.07
     HTML
    -0.07
     structures
    -0.07
     Batt
    -0.07
     transmission
    -0.06
     basil
    -0.06
     Sit
    -0.06
     contracting
    -0.06
    ot
    -0.06
    POSITIVE LOGITS
    ِين
    0.07
    .Player
    0.07
    ्थन
    0.06
     зай
    0.06
    ерь
    0.06
    ScrollPane
    0.06
     �
    0.06
     čís
    0.06
    ANTS
    0.06
    ısıyla
    0.06
    Activations Density 0.009%

    No Known Activations