© 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. 858
    Prev
    Next
    INDEX
    Explanations

    components and ingredients with specific utility or implications

    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
    voke
    -0.06
     hybrid
    -0.06
    erta
    -0.06
    -quality
    -0.06
    mes
    -0.06
     Hybrid
    -0.06
    brands
    -0.05
     подой
    -0.05
     Praha
    -0.05
    fos
    -0.05
    POSITIVE LOGITS
     versatile
    0.09
    glich
    0.08
    OLON
    0.07
    ãĤĴ使
    0.07
     DISCLAIM
    0.07
     versatility
    0.07
     íĻľìļ©
    0.07
    umni
    0.06
    ogui
    0.06
    uggle
    0.06
    Activations Density 0.028%

    No Known Activations