© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 82847
    Prev
    Next
    INDEX
    Explanations

    references to cultural and educational contributions

    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
    álu
    -0.07
    chyb
    -0.07
    advisor
    -0.06
    ाà¤ĩन
    -0.06
    ampler
    -0.06
    +a
    -0.06
    ẩu
    -0.06
     avis
    -0.06
     باÙĦÙĨ
    -0.06
    ĵĺ
    -0.06
    POSITIVE LOGITS
     E
    0.10
     ãĤ¨
    0.09
    ãģĪ
    0.08
     Ñį
    0.08
    .E
    0.08
     е
    0.08
    _E
    0.08
     e
    0.08
    à§ĩ
    0.08
     ÐŃ
    0.08
    Activations Density 0.517%

    No Known Activations