© 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. 14306
    Prev
    Next
    INDEX
    Explanations

    statements reflecting commitment to sustainability and social responsibility

    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
     Suff
    -0.07
    anova
    -0.06
    subs
    -0.06
    ha
    -0.06
    Enough
    -0.05
    hl
    -0.05
     Dont
    -0.05
    bia
    -0.05
    bl
    -0.05
    zw
    -0.05
    POSITIVE LOGITS
     potentially
    0.12
     might
    0.10
    pot
    0.09
     could
    0.09
    might
    0.09
     may
    0.08
     possibly
    0.08
     könnte
    0.07
     Could
    0.07
    may
    0.07
    Activations Density 0.044%

    No Known Activations