© 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. 53741
    Prev
    Next
    INDEX
    Explanations

    phrases indicating methods of action or means of execution

    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
    unce
    -0.08
    itere
    -0.07
    erm
    -0.07
    stdin
    -0.07
    )((((
    -0.07
    /left
    -0.07
    .inline
    -0.07
    ä¸įåĪ°
    -0.07
    tring
    -0.07
    057
    -0.06
    POSITIVE LOGITS
     either
    0.12
    either
    0.09
     EITHER
    0.08
     Either
    0.08
     appropriate
    0.07
    Either
    0.07
     corresponding
    0.07
     compatible
    0.06
     suitable
    0.06
     via
    0.06
    Activations Density 0.034%

    No Known Activations