© 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. 76310
    Prev
    Next
    INDEX
    Explanations

    technical terms and error messages related to server 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
    egan
    -0.08
    orget
    -0.08
    kus
    -0.07
    écial
    -0.07
    omaly
    -0.07
    lius
    -0.07
     ëĦ¤ìĿ´íĬ¸
    -0.07
    bane
    -0.07
    remium
    -0.07
    antt
    -0.07
    POSITIVE LOGITS
     Georgia
    0.07
     tact
    0.06
     Louisiana
    0.06
     Lua
    0.06
     ngx
    0.06
     Ala
    0.06
     Reign
    0.06
     Georgian
    0.06
    ray
    0.06
     Alabama
    0.06
    Activations Density 0.008%

    No Known Activations