© 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. 16181
    Prev
    Next
    INDEX
    Explanations

    terms associated with utilities and utility-related 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
    pu
    -0.09
    ned
    -0.08
    ners
    -0.08
    443
    -0.08
    ymous
    -0.07
    rst
    -0.07
    oe
    -0.07
    à¹Ĩ
    -0.07
    ffect
    -0.07
    iz
    -0.07
    POSITIVE LOGITS
    UGH
    0.07
    /utility
    0.07
    áng
    0.07
    ties
    0.07
    ells
    0.06
    ellen
    0.06
    alom
    0.06
    ุม
    0.06
    endale
    0.06
    lander
    0.06
    Activations Density 0.005%

    No Known Activations