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. 22-LLAMASCOPE-RES-131K
    6. 5573
    Prev
    Next
    INDEX
    Explanations

    terms related to quantitative analysis and price metrics in financial contexts

    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
    aver
    -0.07
    ipo
    -0.07
    avers
    -0.07
     Gal
    -0.06
    urn
    -0.06
    ár
    -0.06
    esc
    -0.06
     ping
    -0.06
     Scr
    -0.06
    _macros
    -0.06
    POSITIVE LOGITS
    mina
    0.07
    ullo
    0.07
    IALOG
    0.07
    ushi
    0.07
    inema
    0.07
    odo
    0.07
    yme
    0.07
    igsaw
    0.06
    оза
    0.06
     Mec
    0.06
    Activations Density 0.031%

    No Known Activations