© 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. 127087
    Prev
    Next
    INDEX
    Explanations

    references to themes related to conferences, events, or exhibitions

    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
    elian
    -0.07
     å¸Ĥ
    -0.06
     Caldwell
    -0.06
    stery
    -0.06
     holy
    -0.06
    agua
    -0.06
     rival
    -0.06
    ÙĪØ·
    -0.06
     redd
    -0.06
     пÑĢеÑģÑĤ
    -0.05
    POSITIVE LOGITS
    ä»Ĭå¹´
    0.08
     theme
    0.08
    prompt
    0.07
    oload
    0.07
    theme
    0.07
     tema
    0.07
    /theme
    0.07
    decl
    0.07
    clared
    0.07
    -theme
    0.07
    Activations Density 0.010%

    No Known Activations