© 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. 9-LLAMASCOPE-RES-131K
    11. 99126
    Prev
    Next
    INDEX
    Explanations

    terms related to structured support and resources for entrepreneurs

    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
    ptrdiff
    -0.08
    :CGRect
    -0.07
    sky
    -0.07
    اس
    -0.07
    nore
    -0.06
    atat
    -0.06
    orb
    -0.06
     skim
    -0.06
    ija
    -0.06
    ertest
    -0.06
    POSITIVE LOGITS
    zÄĻ
    0.07
    оÑħ
    0.06
    ["$
    0.06
     imm
    0.06
    RuntimeObject
    0.06
    azed
    0.06
     rig
    0.06
    å¾ģ
    0.06
     gal
    0.06
    å°ĩ
    0.06
    Activations Density 0.023%

    No Known Activations