© 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. 116737
    Prev
    Next
    INDEX
    Explanations

    numerical measurements and dimensions related to objects, particularly in a technical or descriptive context

    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
     fur
    -0.07
    sg
    -0.06
     Fur
    -0.06
    SG
    -0.06
    aran
    -0.06
    osy
    -0.06
    fur
    -0.06
     мил
    -0.06
    elf
    -0.06
    goo
    -0.06
    POSITIVE LOGITS
     diameter
    0.09
    -radius
    0.08
     radius
    0.07
    agnitude
    0.07
    -wide
    0.07
    radius
    0.07
    -high
    0.07
    MaxY
    0.07
     circumference
    0.07
     Diameter
    0.07
    Activations Density 0.027%

    No Known Activations