© 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. 75891
    Prev
    Next
    INDEX
    Explanations

    advice or important information to convey

    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
    iou
    -0.07
    obo
    -0.07
    cro
    -0.06
    icio
    -0.06
    TRACE
    -0.06
    agon
    -0.06
    ilip
    -0.06
    laÄį
    -0.06
    Enough
    -0.06
     sok
    -0.06
    POSITIVE LOGITS
     points
    0.08
     important
    0.07
     tips
    0.07
     Points
    0.07
     note
    0.07
     Cave
    0.07
     rules
    0.07
     ca
    0.07
     Note
    0.06
     cave
    0.06
    Activations Density 0.026%

    No Known Activations