© 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. 116600
    Prev
    Next
    INDEX
    Explanations

    statistics and percentages related to growth or change in various metrics

    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
    tuÄŁ
    -0.07
    acman
    -0.07
    riott
    -0.07
     prostitu
    -0.07
    äch
    -0.07
    ssf
    -0.07
    assi
    -0.06
    pear
    -0.06
    aepernick
    -0.06
    į°
    -0.06
    POSITIVE LOGITS
    kb
    0.06
     Sanford
    0.06
     Tunnel
    0.06
     since
    0.05
     from
    0.05
    fly
    0.05
    flight
    0.05
    arga
    0.05
     tunnel
    0.05
     dy
    0.05
    Activations Density 0.007%

    No Known Activations