© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74354
    Prev
    Next
    INDEX
    Explanations

    phrases indicating spatial dimensions and descriptions of locations

    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
    ectl
    -0.07
    ICES
    -0.07
     Gateway
    -0.06
    lei
    -0.06
    uien
    -0.06
    ipp
    -0.06
     sup
    -0.06
     Soph
    -0.06
    inia
    -0.06
     Vari
    -0.06
    POSITIVE LOGITS
    ">//
    0.08
    igg
    0.07
    compound
    0.07
     grounds
    0.07
    516
    0.07
    /wiki
    0.07
    ãĥ³ãĥĸ
    0.07
    147
    0.07
    grounds
    0.07
    æķ´ä¸ª
    0.07
    Activations Density 0.017%

    No Known Activations