© 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. 1383
    Prev
    Next
    INDEX
    Explanations

    conditional phrases indicating duration or requirements

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    arma
    -0.06
     Regulation
    -0.06
     often
    -0.05
     adapt
    -0.05
    fg
    -0.05
     adap
    -0.05
     relaxation
    -0.05
    ux
    -0.05
    adx
    -0.05
    iu
    -0.05
    POSITIVE LOGITS
     remain
    0.11
     remains
    0.11
     continue
    0.11
     continues
    0.10
     remained
    0.10
    remain
    0.10
     continued
    0.10
    continue
    0.09
    Continue
    0.09
    ä¸ĭåİ»
    0.09
    Activations Density 0.017%

    No Known Activations