© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3844
    Prev
    Next
    INDEX
    Explanations

    mentions of financial transactions and investment activities

    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
    ledon
    -0.06
    bir
    -0.06
     carrier
    -0.06
    pine
    -0.06
    bÃŃr
    -0.06
    832
    -0.06
    adow
    -0.06
    lectron
    -0.06
    ABC
    -0.06
     formally
    -0.06
    POSITIVE LOGITS
     Towers
    0.07
     activity
    0.07
    publish
    0.07
    طار
    0.07
     Activity
    0.07
    -deals
    0.07
     ctype
    0.07
    èĽ
    0.07
     global
    0.06
     globally
    0.06
    Activations Density 0.003%

    No Known Activations