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. 44148
    Prev
    Next
    INDEX
    Explanations

    occurrences of the character "Ï" and its variants in different 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
     kê
    -0.06
     retaliation
    -0.06
     patriotism
    -0.05
    outers
    -0.05
    rieg
    -0.05
     retirement
    -0.05
    privacy
    -0.05
    afen
    -0.05
    cheduled
    -0.05
    竣
    -0.05
    POSITIVE LOGITS
     Story
    0.11
    Story
    0.10
     storytelling
    0.10
     storyt
    0.10
     Craft
    0.10
     STORY
    0.10
     story
    0.09
     Technique
    0.09
     Style
    0.09
     craft
    0.09
    Activations Density 0.009%

    No Known Activations