© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80868
    Prev
    Next
    INDEX
    Explanations

    phrases indicating beliefs, perceptions, or assumptions about situations or outcomes

    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
     Laur
    -0.06
    éro
    -0.06
    burgh
    -0.06
    èªĮ
    -0.06
    STANCE
    -0.06
    isin
    -0.06
     Zuk
    -0.06
    ablo
    -0.06
    igr
    -0.06
    ond
    -0.06
    POSITIVE LOGITS
     termed
    0.07
     Rosenstein
    0.07
    Called
    0.07
    625
    0.06
     called
    0.06
    æĺ¯ä¸Ģ个
    0.06
    inyin
    0.06
    chet
    0.06
    steder
    0.06
    871
    0.06
    Activations Density 0.016%

    No Known Activations