© 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. 80888
    Prev
    Next
    INDEX
    Explanations

    currency symbols and programming syntax

    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
    antry
    -0.07
    ullan
    -0.07
    monic
    -0.07
    ritten
    -0.07
    зÑĮ
    -0.07
    uele
    -0.07
    arro
    -0.06
    ule
    -0.06
    aus
    -0.06
    ifier
    -0.06
    POSITIVE LOGITS
    ç°
    0.06
    chwitz
    0.06
     Holl
    0.06
    tem
    0.06
     Hod
    0.06
    .xtext
    0.05
    ÑĢÑĥÑĤ
    0.05
     ”
    0.05
     ‘
    0.05
     Chu
    0.05
    Activations Density 0.001%

    No Known Activations