© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82791
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and variable assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ple
    -0.07
    梨
    -0.07
     sidel
    -0.06
    eed
    -0.06
    phia
    -0.06
    éĿ
    -0.06
    ÃŃcio
    -0.06
     Skeleton
    -0.06
     enumer
    -0.06
    ici
    -0.06
    POSITIVE LOGITS
    .Split
    0.12
    .split
    0.12
     split
    0.12
     Split
    0.11
    split
    0.10
    Split
    0.10
     splitting
    0.10
    _splits
    0.10
    (split
    0.10
    _split
    0.09
    Activations Density 0.009%

    No Known Activations