© 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. 106701
    Prev
    Next
    INDEX
    Explanations

    references to coding examples and documentation in API or software development contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Examples, tutorials, samples, and other learning resources in technical documentation or developer materials.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    TABLE
    -0.06
     nal
    -0.06
     TABLE
    -0.06
     organic
    -0.06
    Calibri
    -0.06
    ÑĨиÑĤ
    -0.06
    ilor
    -0.05
     WH
    -0.05
    ilin
    -0.05
    éĢ²
    -0.05
    POSITIVE LOGITS
     Demon
    0.10
     Demonstr
    0.10
    examples
    0.10
    demo
    0.10
     example
    0.10
     examples
    0.10
     Examples
    0.10
     demos
    0.09
     demo
    0.09
     demonstrators
    0.09
    Activations Density 0.041%

    No Known Activations