© 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. 27300
    Prev
    Next
    INDEX
    Explanations

    references to time and sequencing within narratives

    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
     Bilim
    -0.07
    ä»Ļ
    -0.07
     vai
    -0.06
    ợ
    -0.06
    hal
    -0.06
    uet
    -0.06
    åĨ
    -0.06
    ãĥ¼ãĥŀ
    -0.06
    avana
    -0.06
    gfx
    -0.06
    POSITIVE LOGITS
    uggle
    0.07
    elligence
    0.07
    ubi
    0.06
     Registry
    0.06
     Hyde
    0.06
     Happ
    0.06
    LOPT
    0.06
    _dash
    0.06
     events
    0.06
     sonrası
    0.06
    Activations Density 0.009%

    No Known Activations