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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 70998
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns and their significance in the text

    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
    utton
    -0.06
    yll
    -0.06
     Gibraltar
    -0.06
     ine
    -0.06
    ular
    -0.06
    tar
    -0.06
     accompanying
    -0.05
    rip
    -0.05
    udder
    -0.05
    etti
    -0.05
    POSITIVE LOGITS
    ChangedEventArgs
    0.07
     Äijiá»ģu
    0.07
    arence
    0.07
     sentiments
    0.07
    preneur
    0.07
    prene
    0.07
     váºŃy
    0.07
     criterion
    0.07
    oxid
    0.07
     Emerging
    0.07
    Activations Density 0.068%

    No Known Activations