© 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. 9-LLAMASCOPE-RES-131K
    11. 98989
    Prev
    Next
    INDEX
    Explanations

    references to quantities and numerical values

    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
    ior
    -0.07
    empor
    -0.07
    291
    -0.06
    598
    -0.06
    ias
    -0.06
    opia
    -0.06
    lej
    -0.06
    298
    -0.06
    500
    -0.06
     sore
    -0.06
    POSITIVE LOGITS
    quam
    0.07
    tdown
    0.07
    ways
    0.07
    celik
    0.06
    ,[],
    0.06
    swick
    0.06
    uls
    0.06
    дал
    0.06
    .dataTables
    0.06
     seperate
    0.06
    Activations Density 0.020%

    No Known Activations