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. 31-LLAMASCOPE-RES-131K
    6. 44243
    Prev
    Next
    INDEX
    Explanations

    adverbs and descriptive phrases that indicate a degree or manner

    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
     Blades
    -0.07
    LOCKS
    -0.06
     weiber
    -0.06
     ÑģмеÑģÑĮ
    -0.06
    WORDS
    -0.06
    apor
    -0.06
     Walls
    -0.06
     readily
    -0.06
     Tubes
    -0.06
     Bones
    -0.06
    POSITIVE LOGITS
     cont
    0.09
     var
    0.09
     dom
    0.09
     pattern
    0.09
     ve
    0.09
     lac
    0.09
     jew
    0.08
     budd
    0.08
     wrink
    0.08
     joint
    0.08
    Activations Density 0.034%

    No Known Activations