© 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. 121280
    Prev
    Next
    INDEX
    Explanations

    references to licenses and copyright information

    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
     od
    -0.07
     inf
    -0.06
    6
    -0.06
     sm
    -0.06
     ill
    -0.06
    3
    -0.06
     att
    -0.06
    å·
    -0.05
     slightly
    -0.05
    5
    -0.05
    POSITIVE LOGITS
    GuidId
    0.08
    AdapterManager
    0.08
    fak
    0.08
    AdapterFactory
    0.08
    è®®
    0.08
    affles
    0.07
    ÑĢоÑİ
    0.07
     ÑĩаÑģом
    0.07
    .sponge
    0.07
     *__
    0.07
    Activations Density 0.002%

    No Known Activations