© 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. 103747
    Prev
    Next
    INDEX
    Explanations

    references to managed care and related health services contracts

    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
    _serial
    -0.07
    OffsetTable
    -0.06
    PÅĻi
    -0.06
    ëľ
    -0.06
    иÑģÑĤÑĢа
    -0.06
    gist
    -0.06
     stag
    -0.06
    chwitz
    -0.06
    stag
    -0.06
    Tween
    -0.06
    POSITIVE LOGITS
    há
    0.06
    776
    0.06
    446
    0.06
     solution
    0.06
    olarity
    0.06
    rips
    0.06
     Inc
    0.06
     solutions
    0.06
     {{↵
    0.06
    uman
    0.06
    Activations Density 0.031%

    No Known Activations