© 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. 15-LLAMASCOPE-RES-131K
    11. 61678
    Prev
    Next
    INDEX
    Explanations

    references to scientific keywords and academic structures in research articles

    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
    ublisher
    -0.06
     perch
    -0.06
     fibre
    -0.06
    è¦ļ
    -0.06
     Sul
    -0.06
    vip
    -0.06
    alars
    -0.06
    ayload
    -0.06
    atik
    -0.06
    uchen
    -0.06
    POSITIVE LOGITS
    ISCO
    0.08
    itzer
    0.07
    andon
    0.07
    ä¸į足
    0.07
    cede
    0.06
    graf
    0.06
    ohn
    0.06
    ãĥ¼ãĥį
    0.06
    umed
    0.06
    uele
    0.06
    Activations Density 0.000%

    No Known Activations