© 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. 89950
    Prev
    Next
    INDEX
    Explanations

    references to the access and release of information and documents

    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
    endor
    -0.08
     bras
    -0.07
    rego
    -0.07
    å¢
    -0.07
    nge
    -0.07
    ango
    -0.07
    appable
    -0.06
    ãĥ¬ãĥ³
    -0.06
    enez
    -0.06
    ENDOR
    -0.06
    POSITIVE LOGITS
     sharing
    0.07
     requested
    0.06
    ovsky
    0.06
    Ł³
    0.06
     Sharing
    0.06
     Meadows
    0.06
    aed
    0.06
    ause
    0.06
    -sharing
    0.06
    elay
    0.06
    Activations Density 0.019%

    No Known Activations