© 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. 5-LLAMASCOPE-RES-131K
    11. 126483
    Prev
    Next
    INDEX
    Explanations

    frequent mentions of dates or temporal 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
    ette
    -0.07
    UI
    -0.06
     hyp
    -0.06
    esc
    -0.06
    olet
    -0.06
    azzi
    -0.06
    استاÙĨ
    -0.06
     py
    -0.05
    ooks
    -0.05
    CI
    -0.05
    POSITIVE LOGITS
     Lup
    0.08
    ANNEL
    0.07
    fat
    0.07
    %)↵↵
    0.07
    PointerException
    0.07
    illard
    0.06
    cold
    0.06
    itmap
    0.06
    ISTRIBUT
    0.06
     Rip
    0.06
    Activations Density 0.003%

    No Known Activations