© 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. 15-LLAMASCOPE-RES-131K
    11. 765
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "public" in programming or technical contexts

    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
    azon
    -0.08
    Äħż
    -0.07
    lobals
    -0.06
    uyu
    -0.06
    æ´¥
    -0.06
     mož
    -0.06
     Jong
    -0.06
    oran
    -0.06
    å·Ŀ
    -0.06
    IL
    -0.06
    POSITIVE LOGITS
    clud
    0.07
    AccessorType
    0.07
     جغراÙģ
    0.06
    237
    0.06
    omm
    0.06
    acht
    0.06
    _footer
    0.06
    _restart
    0.06
    OUCH
    0.06
    343
    0.05
    Activations Density 0.000%

    No Known Activations