© 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 EvalsExportsinterp-engineNEWAPI 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. 92634
    Prev
    Next
    INDEX
    Explanations

    references to spatial requirements and accommodations

    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
    owl
    -0.07
    hot
    -0.07
    -hot
    -0.06
    684
    -0.06
    996
    -0.06
    965
    -0.06
    Touches
    -0.06
    à¥įत
    -0.06
    _hot
    -0.06
    tery
    -0.06
    POSITIVE LOGITS
     preferably
    0.08
    Ide
    0.07
     Ideally
    0.07
     ideally
    0.06
     ÑĢÑıдом
    0.06
     ideal
    0.06
    ichen
    0.06
    indo
    0.06
    bens
    0.06
    éré
    0.06
    Activations Density 0.019%

    No Known Activations