© 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. 69145
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or expressions of disagreement

    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
    oles
    -0.08
    raž
    -0.07
    ura
    -0.07
    otu
    -0.07
    APTER
    -0.07
    anteed
    -0.07
    kla
    -0.07
    rego
    -0.07
    arge
    -0.07
    ulle
    -0.07
    POSITIVE LOGITS
     matter
    0.12
    matter
    0.09
     Matter
    0.08
     longer
    0.07
    isque
    0.06
    928
    0.06
     man
    0.06
     doubt
    0.06
     wonder
    0.06
    etically
    0.05
    Activations Density 0.012%

    No Known Activations