© 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. 69360
    Prev
    Next
    INDEX
    Explanations

    language related to vision or planning for the future

    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
    aurant
    -0.07
    ẹn
    -0.07
    corp
    -0.07
    ante
    -0.06
    eder
    -0.06
    tsky
    -0.06
    itemap
    -0.06
    issen
    -0.06
    ouver
    -0.06
    znik
    -0.05
    POSITIVE LOGITS
     similarly
    0.25
     similar
    0.23
    similar
    0.19
     same
    0.18
     Similarly
    0.18
    Similarly
    0.17
     simil
    0.17
     Similar
    0.16
    Similar
    0.16
    缸åIJĮ
    0.15
    Activations Density 0.061%

    No Known Activations