© 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. 81690
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to mathematical theorems and proofs

    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
    od
    -0.08
    978
    -0.06
    uant
    -0.06
    bai
    -0.06
    urf
    -0.06
     ambigu
    -0.06
    uch
    -0.06
    rame
    -0.06
    681
    -0.06
    omid
    -0.06
    POSITIVE LOGITS
     gap
    0.07
     Gap
    0.07
     prov
    0.07
    FLASH
    0.06
    _sep
    0.06
    опол
    0.06
     تÙĤÙĪ
    0.06
    gap
    0.06
     progress
    0.06
    _INFINITY
    0.06
    Activations Density 0.061%

    No Known Activations