© 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. 80532
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and symbols related to equations and inequalities

    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
    oÅĻ
    -0.07
     UObject
    -0.07
    Indexed
    -0.07
    uky
    -0.07
    .cx
    -0.07
     parseFloat
    -0.07
     repmat
    -0.06
     srand
    -0.06
    857
    -0.06
    ãĥ³ãĥIJ
    -0.06
    POSITIVE LOGITS
    ystal
    0.06
     economies
    0.06
    IRMWARE
    0.06
    SA
    0.06
     Hor
    0.06
     Haw
    0.06
     strict
    0.05
    åĭ
    0.05
    å¹
    0.05
    ưỡng
    0.05
    Activations Density 0.219%

    No Known Activations