© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61751
    Prev
    Next
    INDEX
    Explanations

    references to search engines and their roles in web content ranking

    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
    odor
    -0.08
    amba
    -0.07
    eto
    -0.06
    odo
    -0.06
    ord
    -0.06
    aday
    -0.06
    ure
    -0.06
     pseud
    -0.06
    color
    -0.06
    oken
    -0.06
    POSITIVE LOGITS
    åύ
    0.08
    isku
    0.07
    dex
    0.07
    adiens
    0.07
    tent
    0.06
    UpDown
    0.06
    /search
    0.06
    егÑĢа
    0.06
    -analytics
    0.06
    ìĿ´íĦ°
    0.06
    Activations Density 0.002%

    No Known Activations