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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5426
    Prev
    Next
    INDEX
    Explanations

    terms related to financial and economic issues

    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
    affen
    -0.07
    akin
    -0.06
    manship
    -0.06
    ivol
    -0.06
    adol
    -0.06
    RIPT
    -0.06
    utto
    -0.06
    leton
    -0.06
    611
    -0.06
    sik
    -0.06
    POSITIVE LOGITS
    Unused
    0.08
    大åħ¨
    0.07
     Zus
    0.07
    ous
    0.07
    CMS
    0.06
    .sent
    0.06
    ["$
    0.06
    orida
    0.06
    comb
    0.06
    олÑİ
    0.06
    Activations Density 0.004%

    No Known Activations