© 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. 117982
    Prev
    Next
    INDEX
    Explanations

    references to historical context and events

    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
    ctrine
    -0.07
    ovnÃŃ
    -0.07
     Insecta
    -0.07
    oles
    -0.07
     æľ¨
    -0.07
    äºķ
    -0.07
    èijī
    -0.07
     Sesso
    -0.07
     maduras
    -0.07
    åı¶
    -0.07
    POSITIVE LOGITS
     ice
    0.08
     Ice
    0.08
    KT
    0.07
    ache
    0.07
    rawn
    0.07
     mam
    0.07
    rame
    0.06
     Paleo
    0.06
     prime
    0.06
     ext
    0.06
    Activations Density 0.017%

    No Known Activations