© 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. 123737
    Prev
    Next
    INDEX
    Explanations

    phrases indicating adjustments or modifications made to existing systems or processes

    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
    /reset
    -0.08
    umd
    -0.07
    FullPath
    -0.07
     quo
    -0.07
    á»Ļ
    -0.07
    tek
    -0.06
     seins
    -0.06
    -git
    -0.06
    /install
    -0.06
     kvinde
    -0.06
    POSITIVE LOGITS
     changes
    0.14
     slight
    0.12
    changes
    0.12
     modifications
    0.11
     Changes
    0.11
     change
    0.11
     changed
    0.10
    Changes
    0.10
     slightly
    0.10
     minor
    0.10
    Activations Density 0.028%

    No Known Activations