© 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. 28815
    Prev
    Next
    INDEX
    Explanations

    connections between organizations, values, and shared commitments

    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
    )prepare
    -0.08
    uito
    -0.07
    arih
    -0.07
     зави
    -0.07
    voke
    -0.07
    erk
    -0.07
    rotein
    -0.07
    ź
    -0.07
    /desktop
    -0.07
    idity
    -0.06
    POSITIVE LOGITS
     similar
    0.11
     same
    0.11
     values
    0.10
     shared
    0.09
    ä¸Ģæł·
    0.09
    shared
    0.09
    åIJĮãģĺ
    0.09
     mutual
    0.09
    缸åIJĮ
    0.09
    same
    0.09
    Activations Density 0.038%

    No Known Activations