© 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. 15-LLAMASCOPE-RES-131K
    11. 88333
    Prev
    Next
    INDEX
    Explanations

    programming or structural elements within a code or markup context

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

    Markup language syntax elements and formatting commands that control how content is rendered or displayed in documents.

    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
    rve
    -0.06
    amed
    -0.06
    .Exit
    -0.06
    .LookAndFeel
    -0.06
    anti
    -0.06
    phabet
    -0.05
    art
    -0.05
     Exit
    -0.05
    urr
    -0.05
    rew
    -0.05
    POSITIVE LOGITS
    kers
    0.08
    ãĥªãĤ¢
    0.07
    Cop
    0.07
     Ãľl
    0.07
    æ£
    0.07
    Area
    0.07
    uteur
    0.07
    еÐ
    0.07
    ç·
    0.07
    .returnValue
    0.07
    Activations Density 0.049%

    No Known Activations