© 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. 16526
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and indicators of uncertainty or question

    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
     Sher
    -0.06
    Compiled
    -0.06
    zap
    -0.06
     Surf
    -0.06
    reet
    -0.06
     Morph
    -0.06
     Compiled
    -0.06
    Pie
    -0.06
     Gilbert
    -0.06
    ersed
    -0.06
    POSITIVE LOGITS
    üm
    0.07
     Tender
    0.07
    rites
    0.06
     cres
    0.06
    ÑıÑĤ
    0.06
     Smy
    0.06
    eu
    0.06
    /callback
    0.06
    ruptcy
    0.06
    presso
    0.06
    Activations Density 0.005%

    No Known Activations