© 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. 91509
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating achievement or engagement

    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
    illis
    -0.08
    elder
    -0.07
    ndon
    -0.07
    outh
    -0.07
    èĬĿ
    -0.07
    iens
    -0.06
    ÑĪÑĥ
    -0.06
    ied
    -0.06
    oste
    -0.06
     figure
    -0.06
    POSITIVE LOGITS
    AGMA
    0.07
    ephir
    0.07
     us
    0.07
     ìŬ룬ë¶Ħ
    0.07
    bcm
    0.07
    byname
    0.07
    ewidth
    0.06
    ibri
    0.06
     you
    0.06
    emarks
    0.06
    Activations Density 0.018%

    No Known Activations