© 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. 42771
    Prev
    Next
    INDEX
    Explanations

    specific data points and numerical references within scientific contexts

    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
    ượt
    -0.06
    οÏħ
    -0.06
    273
    -0.06
    rain
    -0.06
    conomy
    -0.06
    igth
    -0.06
    rw
    -0.06
    orer
    -0.05
     press
    -0.05
    lagen
    -0.05
    POSITIVE LOGITS
    RIORITY
    0.08
    inary
    0.07
    abric
    0.07
    culus
    0.07
    ">//
    0.07
    بش
    0.06
     filmer
    0.06
    ÏĢλ
    0.06
    ecta
    0.06
    ãģ«ãĤĪ
    0.06
    Activations Density 0.008%

    No Known Activations