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. 43530
    Prev
    Next
    INDEX
    Explanations

    non-standard characters or symbols in the text

    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
     utilise
    -0.07
     util
    -0.07
     Teen
    -0.06
     Emoji
    -0.06
     continual
    -0.06
     Adult
    -0.06
     teens
    -0.06
     teen
    -0.06
     Cara
    -0.06
     emoji
    -0.06
    POSITIVE LOGITS
     Faculty
    0.10
    Faculty
    0.09
     Campus
    0.08
     Sciences
    0.08
    UB
    0.08
     UCLA
    0.08
     faculty
    0.08
     NSF
    0.08
     Universities
    0.08
    UGC
    0.08
    Activations Density 0.003%

    No Known Activations