© 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. 84344
    Prev
    Next
    INDEX
    Explanations

    specific details about event organization and logistics

    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
    æĺŃ
    -0.07
    ania
    -0.07
    CellValue
    -0.07
    .scalablytyped
    -0.07
    Ñħодим
    -0.06
     thủy
    -0.06
    alara
    -0.06
    ACHER
    -0.06
    arih
    -0.06
    antom
    -0.06
    POSITIVE LOGITS
     tents
    0.16
     tent
    0.13
    tent
    0.11
     Tent
    0.10
     portable
    0.09
     booths
    0.09
     Portable
    0.09
     camp
    0.09
     temporary
    0.09
    Portable
    0.09
    Activations Density 0.161%

    No Known Activations