© 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. 126767
    Prev
    Next
    INDEX
    Explanations

    keywords related to global challenges and opportunities in various markets

    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
    åħ¨åĽ½
    -0.07
    urre
    -0.07
    HEEL
    -0.07
    ysqli
    -0.07
    StateException
    -0.06
    aurus
    -0.06
    astro
    -0.06
    orian
    -0.06
    .gwt
    -0.06
     Geç
    -0.06
    POSITIVE LOGITS
    /world
    0.10
    /global
    0.10
    ToLocal
    0.08
    (Global
    0.08
    (global
    0.08
    -global
    0.07
     standards
    0.07
     Global
    0.07
     global
    0.07
    ól
    0.07
    Activations Density 0.080%

    No Known Activations