© 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. 125929
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to conditions and warranties

    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
    eus
    -0.08
     NDEBUG
    -0.07
    uede
    -0.07
    arus
    -0.07
    RAR
    -0.07
    erea
    -0.07
    Paste
    -0.07
    è³¢
    -0.07
    áp
    -0.07
    uya
    -0.07
    POSITIVE LOGITS
     Fountain
    0.06
    ÑĤал
    0.06
     verz
    0.06
     Mot
    0.06
     Republic
    0.06
     nowrap
    0.06
    chie
    0.05
     alt
    0.05
    ÏĦα
    0.05
    eton
    0.05
    Activations Density 0.001%

    No Known Activations