© 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. 120055
    Prev
    Next
    INDEX
    Explanations

    references to advisory councils and committees and their functions

    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
    ilis
    -0.09
    assa
    -0.07
     responseType
    -0.07
    edic
    -0.07
    buie
    -0.07
    hausen
    -0.07
    haft
    -0.07
    ÑĭÑĤ
    -0.07
    hiba
    -0.06
    undle
    -0.06
    POSITIVE LOGITS
     composition
    0.10
     members
    0.09
    composition
    0.09
     membership
    0.09
     compositions
    0.09
    Composition
    0.09
     Composition
    0.08
    members
    0.08
     formed
    0.08
    composed
    0.08
    Activations Density 0.025%

    No Known Activations