© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29345
    Prev
    Next
    INDEX
    Explanations

    phrases that express contrast or opposition

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ancia
    -0.07
    .must
    -0.07
    zos
    -0.07
     sice
    -0.07
     ë¿IJ
    -0.07
    bak
    -0.07
    UGE
    -0.07
    NotNull
    -0.06
     ikke
    -0.06
    uang
    -0.06
    POSITIVE LOGITS
     actual
    0.11
     actually
    0.09
    actual
    0.08
     proper
    0.08
     Actually
    0.08
     Actual
    0.08
    Actually
    0.08
    羣æŃ£
    0.07
     real
    0.07
    (actual
    0.07
    Activations Density 0.039%

    No Known Activations