© 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. 96091
    Prev
    Next
    INDEX
    Explanations

    the word "it" emphasizing its significance in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    unk
    -0.07
    hd
    -0.07
     Br
    -0.06
    kv
    -0.06
    mund
    -0.06
     fas
    -0.06
    qv
    -0.06
    ulture
    -0.06
    ´
    -0.06
    stag
    -0.06
    POSITIVE LOGITS
    ched
    0.08
    inerary
    0.08
    iner
    0.07
     fetisch
    0.07
    oplevel
    0.07
    ìłĢ
    0.07
     Erotische
    0.07
    abouts
    0.07
     setBackgroundColor
    0.07
    ABCDEFGHIJKLMNOP
    0.07
    Activations Density 0.003%

    No Known Activations