© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 54070
    Prev
    Next
    INDEX
    Explanations

    terms related to resetting processes or protocols

    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
    erb
    -0.09
    iciones
    -0.08
    keit
    -0.08
    aug
    -0.07
    isy
    -0.07
    fare
    -0.07
    outh
    -0.07
    ร
    -0.07
    astr
    -0.07
    ìļĶ
    -0.07
    POSITIVE LOGITS
    ting
    0.12
    ters
    0.10
    tings
    0.10
    table
    0.10
    ted
    0.09
    tle
    0.08
    tement
    0.08
    tables
    0.08
    tt
    0.08
    ively
    0.07
    Activations Density 0.006%

    No Known Activations