© 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. 14434
    Prev
    Next
    INDEX
    Explanations

    references to career and professional experiences

    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
    burgh
    -0.07
    tual
    -0.07
    urg
    -0.06
    nda
    -0.06
    ropa
    -0.06
    _mgr
    -0.06
    ago
    -0.06
     saddle
    -0.06
    rada
    -0.06
    966
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.09
    \core
    0.07
    .Option
    0.07
    isting
    0.07
    AME
    0.06
    sing
    0.06
    iev
    0.06
    allas
    0.06
    رØŃ
    0.06
    .acc
    0.06
    Activations Density 0.010%

    No Known Activations