© 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. 82556
    Prev
    Next
    INDEX
    Explanations

    references to server environment variables and configurations

    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
    suspend
    -0.07
    ÏĢον
    -0.07
     arac
    -0.06
    oris
    -0.06
    vation
    -0.06
    StandardItem
    -0.06
    ISTRY
    -0.06
    _MOUSE
    -0.06
    ån
    -0.06
     PACK
    -0.06
    POSITIVE LOGITS
     production
    0.09
     environment
    0.09
     environments
    0.08
     Production
    0.08
     dev
    0.08
     Prod
    0.08
    -production
    0.07
    production
    0.07
     run
    0.07
     conditions
    0.07
    Activations Density 0.014%

    No Known Activations