© 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. 89601
    Prev
    Next
    INDEX
    Explanations

    numerical values and references to specific quantities

    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
    aoke
    -0.06
     pose
    -0.06
    auer
    -0.06
     Ding
    -0.06
    ridge
    -0.06
    _pose
    -0.06
     INST
    -0.06
    ,[],
    -0.06
     Access
    -0.06
     playa
    -0.06
    POSITIVE LOGITS
    orio
    0.08
     Animator
    0.07
    stroy
    0.07
     GK
    0.07
    ãĤ¢ãĥĭãĥ¡
    0.07
     animator
    0.07
    enco
    0.07
    .Children
    0.07
     Pixar
    0.07
    mits
    0.07
    Activations Density 0.001%

    No Known Activations