© 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. 78879
    Prev
    Next
    INDEX
    Explanations

    mentions of notable individuals and significant dates

    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
     Dün
    -0.07
    .apiUrl
    -0.07
    itele
    -0.07
    urum
    -0.07
    :path
    -0.07
     Richards
    -0.07
    æĸ
    -0.06
    chants
    -0.06
    пеÑĩ
    -0.06
    rech
    -0.06
    POSITIVE LOGITS
    197
    0.10
    196
    0.09
    194
    0.08
    198
    0.08
    192
    0.08
    193
    0.08
    195
    0.08
    191
    0.08
     born
    0.07
    190
    0.07
    Activations Density 0.007%

    No Known Activations