© 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 EvalsExportsinterp-engineNEWAPI 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. 81075
    Prev
    Next
    INDEX
    Explanations

    statistical results from educational assessments

    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
    ascar
    -0.08
    eldorf
    -0.07
     eldre
    -0.07
    elho
    -0.07
    omics
    -0.07
    -contrib
    -0.07
    lect
    -0.07
    _Runtime
    -0.07
     numel
    -0.07
    jem
    -0.07
    POSITIVE LOGITS
     improvement
    0.08
     improvements
    0.07
     Improvement
    0.07
     performance
    0.07
     overall
    0.06
    .performance
    0.06
     raw
    0.06
     diplom
    0.06
    _RAW
    0.06
     Relay
    0.06
    Activations Density 0.005%

    No Known Activations