© 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. 126319
    Prev
    Next
    INDEX
    Explanations

    dates and numerical references

    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
    enga
    -0.07
    hausen
    -0.07
    عب
    -0.07
    uyu
    -0.06
    طار
    -0.06
     ↵↵
    -0.06
    ante
    -0.06
    ãĥ¬ãĤ¤
    -0.06
    ãĢĢ↵
    -0.06
     biom
    -0.06
    POSITIVE LOGITS
    isÃŃ
    0.07
    .IsSuccess
    0.06
    @student
    0.06
    sys
    0.06
    ods
    0.06
    usercontent
    0.06
    ccione
    0.06
    imes
    0.06
     peak
    0.06
    iyas
    0.06
    Activations Density 0.005%

    No Known Activations