© 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. 31418
    Prev
    Next
    INDEX
    Explanations

    references to fundraising and donations

    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
    rypt
    -0.06
     Channels
    -0.06
    alue
    -0.06
     Chan
    -0.06
    orent
    -0.06
    ritt
    -0.06
    rench
    -0.06
     royalties
    -0.06
    iculos
    -0.06
    ilim
    -0.06
    POSITIVE LOGITS
     matched
    0.12
     match
    0.10
     Matching
    0.10
    matched
    0.10
     Matches
    0.10
     matching
    0.10
     matches
    0.10
    -match
    0.09
     matcher
    0.09
    matches
    0.09
    Activations Density 0.014%

    No Known Activations