© 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. 70747
    Prev
    Next
    INDEX
    Explanations

    numerical data related to company shares and financial values

    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
    reater
    -0.07
    uchar
    -0.06
    urch
    -0.06
    ently
    -0.06
     trial
    -0.06
    .bundle
    -0.06
    reserve
    -0.06
    gzip
    -0.06
     fund
    -0.06
    ieder
    -0.06
    POSITIVE LOGITS
    osy
    0.06
    Disclosure
    0.06
     Disclosure
    0.06
     halo
    0.06
    obe
    0.06
    rome
    0.06
     Halo
    0.06
    arrera
    0.06
    oru
    0.06
    olen
    0.06
    Activations Density 0.002%

    No Known Activations