© 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. 53975
    Prev
    Next
    INDEX
    Explanations

    data related to averages and statistical comparisons

    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
    _statuses
    -0.07
    lectron
    -0.07
    ablo
    -0.07
    лÑĥг
    -0.07
     deb
    -0.07
    Liver
    -0.06
    ambi
    -0.06
    lew
    -0.06
    _semaphore
    -0.06
    amac
    -0.06
    POSITIVE LOGITS
     average
    0.13
    å¹³åĿĩ
    0.12
    average
    0.11
     Average
    0.11
    -average
    0.10
     avg
    0.10
    mean
    0.10
     mean
    0.10
    Average
    0.09
     Mean
    0.09
    Activations Density 0.133%

    No Known Activations