© 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. 56543
    Prev
    Next
    INDEX
    Explanations

    references to the concept of discovery

    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
    uth
    -0.08
    usc
    -0.07
    ioned
    -0.07
    ularity
    -0.07
    ãĥ³ãĥij
    -0.07
    ura
    -0.06
    (strpos
    -0.06
     addCriterion
    -0.06
    ural
    -0.06
    ners
    -0.06
    POSITIVE LOGITS
    veloper
    0.07
    áng
    0.07
    edy
    0.06
    fy
    0.06
    aint
    0.06
    ë¡ľìļ´
    0.06
    ivist
    0.06
     eldre
    0.06
    weigh
    0.06
    deb
    0.06
    Activations Density 0.005%

    No Known Activations