© 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. 9-LLAMASCOPE-RES-131K
    11. 95490
    Prev
    Next
    INDEX
    Explanations

    references to technology-related tools or advancements

    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
    ongyang
    -0.07
    iate
    -0.07
    ething
    -0.07
    olang
    -0.07
    TickCount
    -0.07
    ornado
    -0.07
    kyt
    -0.06
    ozor
    -0.06
    /cli
    -0.06
    ç¶ĵ
    -0.06
    POSITIVE LOGITS
    \grid
    0.07
    646
    0.07
    fg
    0.06
    pro
    0.06
    REA
    0.06
    inds
    0.06
    illus
    0.06
    ross
    0.06
    isco
    0.06
     Cald
    0.06
    Activations Density 0.000%

    No Known Activations