© 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. 107167
    Prev
    Next
    INDEX
    Explanations

    references to pronouns indicating subjects in sentences

    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
    IFn
    -0.07
    reste
    -0.07
    одо
    -0.07
    ابÛĮ
    -0.07
    slaught
    -0.07
     totiž
    -0.07
    rzy
    -0.07
    Č
    -0.07
    nable
    -0.07
    .tim
    -0.06
    POSITIVE LOGITS
    501
    0.07
     finished
    0.07
    -même
    0.07
    aved
    0.07
    ched
    0.07
    aving
    0.07
     own
    0.06
    -know
    0.06
    Å¡etÅĻ
    0.06
    iled
    0.06
    Activations Density 0.017%

    No Known Activations