© 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. 57657
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical wiring and its components

    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
    es
    -0.07
     Roch
    -0.07
     spirit
    -0.07
    chod
    -0.07
    icorn
    -0.06
    /big
    -0.06
    inium
    -0.06
    pack
    -0.06
    /bin
    -0.06
    ÄĽk
    -0.06
    POSITIVE LOGITS
    ted
    0.07
    ·
    0.07
     haystack
    0.07
    -Language
    0.07
    (Operation
    0.07
    orr
    0.06
    nowledge
    0.06
     hosp
    0.06
    cheme
    0.06
    /lang
    0.06
    Activations Density 0.003%

    No Known Activations