© 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. 88377
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and version control

    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
    avel
    -0.08
    oload
    -0.08
    lauf
    -0.07
    agi
    -0.07
     Sesso
    -0.07
    åį
    -0.07
    ека
    -0.07
     teb
    -0.07
    ialis
    -0.07
    .Tick
    -0.07
    POSITIVE LOGITS
     committed
    0.07
    isel
    0.06
     changes
    0.06
     staged
    0.06
     lint
    0.06
     tracked
    0.06
     unde
    0.06
     files
    0.05
     patriarch
    0.05
    _sy
    0.05
    Activations Density 0.001%

    No Known Activations