© 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. 1540
    Prev
    Next
    INDEX
    Explanations

    details related to statistical analysis and numerical evaluations

    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
    è¤
    -0.06
     Hod
    -0.06
     ê
    -0.06
    ehr
    -0.06
     Lands
    -0.05
    imore
    -0.05
    _NULL
    -0.05
    ascade
    -0.05
    ibold
    -0.05
     trib
    -0.05
    POSITIVE LOGITS
     count
    0.11
     reported
    0.11
     statistics
    0.10
    -reported
    0.10
     statistic
    0.10
     figures
    0.09
     counts
    0.09
     figure
    0.09
     stats
    0.09
    statistics
    0.09
    Activations Density 0.073%

    No Known Activations