Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43801
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Gree" and related variations

    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
    allon
    -0.06
    moon
    -0.06
     dial
    -0.06
     Cair
    -0.06
    cams
    -0.06
    639
    -0.06
    era
    -0.06
    crypt
    -0.06
    _HP
    -0.06
    asel
    -0.06
    POSITIVE LOGITS
    ley
    0.12
    kt
    0.11
    leys
    0.09
     Belediye
    0.09
    hey
    0.09
    LEY
    0.09
    gle
    0.08
    kr
    0.08
    en
    0.08
    peace
    0.08
    Activations Density 0.003%

    No Known Activations