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

    Neuronpedia

    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. 130122
    Prev
    Next
    INDEX
    Explanations

    references to accountability and oversight in institutional contexts

    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
     addCriterion
    -0.08
    ationship
    -0.08
     Wet
    -0.07
    nech
    -0.07
    assadors
    -0.07
    :CGRect
    -0.07
    auer
    -0.07
    PÅĻi
    -0.07
    ัà¸ķร
    -0.07
    QualifiedName
    -0.07
    POSITIVE LOGITS
     improvement
    0.18
     Improvement
    0.16
     improvements
    0.16
     improve
    0.14
     improving
    0.14
     Impro
    0.13
    Impro
    0.13
     Improve
    0.12
     improves
    0.12
     improved
    0.11
    Activations Density 0.150%

    No Known Activations