© 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. 69367
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts related to options and configurations

    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
    ein
    -0.07
    urum
    -0.07
     Booth
    -0.07
    ledon
    -0.06
    ouro
    -0.06
     raw
    -0.06
    .required
    -0.06
     Rag
    -0.06
    ahl
    -0.06
     pure
    -0.06
    POSITIVE LOGITS
     current
    0.11
    å½ĵåīį
    0.11
    _CURRENT
    0.10
     ÑĤекÑĥÑī
    0.10
    íĺ
    0.10
    current
    0.10
     íĺĦìŀ¬
    0.09
     CURRENT
    0.09
    /current
    0.09
     currently
    0.09
    Activations Density 0.026%

    No Known Activations