© 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. 839
    Prev
    Next
    INDEX
    Explanations

    references to significant entities or concepts

    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
     viá»ĩn
    -0.08
    oming
    -0.08
    riott
    -0.08
    AREN
    -0.08
    ursday
    -0.08
    ucer
    -0.08
    roat
    -0.07
    ISTRIBUT
    -0.07
    peri
    -0.07
    adro
    -0.07
    POSITIVE LOGITS
     di
    0.06
     br
    0.06
    .xhtml
    0.06
    Roll
    0.06
     Roll
    0.06
     roller
    0.06
    å¹³
    0.06
     rolls
    0.06
     Rug
    0.06
     ess
    0.06
    Activations Density 0.038%

    No Known Activations