© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 119353
    Prev
    Next
    INDEX
    Explanations

    programming or coding structures and syntax

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

    Programming code syntax elements, including function modifiers, class names, operators, and whitespace in code alignment.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anzeigen
    -0.07
    uz
    -0.07
     Caucus
    -0.06
    eros
    -0.06
     Lesb
    -0.06
    زÙĪ
    -0.05
    Knife
    -0.05
    rink
    -0.05
    unami
    -0.05
    -aos
    -0.05
    POSITIVE LOGITS
    kus
    0.07
    fak
    0.07
    ÑİÑĢ
    0.07
     Indi
    0.07
    edith
    0.07
    ñas
    0.07
    cker
    0.06
     libertin
    0.06
     McInt
    0.06
    ENCY
    0.06
    Activations Density 0.152%

    No Known Activations