© 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. 5753
    Prev
    Next
    INDEX
    Explanations

    product specifications and accessory details

    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
    adge
    -0.07
    athi
    -0.07
     Platt
    -0.06
    æĸ
    -0.06
    726
    -0.06
    Checksum
    -0.06
    ajo
    -0.06
     spin
    -0.06
     Slam
    -0.05
    ata
    -0.05
    POSITIVE LOGITS
     spare
    0.08
    zas
    0.07
    ahlen
    0.07
     ãĢ
    0.07
     Spare
    0.07
     mắt
    0.07
    reh
    0.07
     Ear
    0.07
    ear
    0.06
     Pose
    0.06
    Activations Density 0.006%

    No Known Activations