© 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. 69391
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and suggestions for improvement or change

    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
     wel
    -0.06
     alternate
    -0.06
     appe
    -0.06
     incumb
    -0.06
    Alternate
    -0.06
     Alternate
    -0.06
    @show
    -0.05
     hum
    -0.05
    oman
    -0.05
    uddle
    -0.05
    POSITIVE LOGITS
     similarly
    0.12
     likewise
    0.10
     Similarly
    0.10
    Similarly
    0.10
     Likewise
    0.09
     ALSO
    0.09
    dit
    0.08
    oux
    0.08
    also
    0.08
    ôm
    0.08
    Activations Density 0.053%

    No Known Activations