© 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. 1536
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of 'the rest of' in various contexts

    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
     among
    -0.07
     enough
    -0.07
     last
    -0.07
     otherwise
    -0.06
    omb
    -0.06
     alas
    -0.06
     rect
    -0.06
     first
    -0.06
     next
    -0.06
     final
    -0.06
    POSITIVE LOGITS
    world
    0.08
    igham
    0.08
    OE
    0.07
    _stuff
    0.07
    atcher
    0.07
    _Tis
    0.07
    STITUTE
    0.07
    ookie
    0.07
    cran
    0.07
    suite
    0.06
    Activations Density 0.012%

    No Known Activations