© 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. 95889
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and software development

    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
    arih
    -0.09
    ılıç
    -0.08
    ippet
    -0.07
    zeich
    -0.07
    adir
    -0.07
    odash
    -0.07
    zeichnet
    -0.07
    ibble
    -0.07
    PLICATE
    -0.07
    ippy
    -0.06
    POSITIVE LOGITS
     từng
    0.07
     ÙĤسÙħ
    0.06
     Lloyd
    0.06
     Brom
    0.06
     Schn
    0.06
     heavily
    0.06
    ucken
    0.05
     dimin
    0.05
    imes
    0.05
    setVisibility
    0.05
    Activations Density 0.000%

    No Known Activations