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. 44112
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters within 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
    PILE
    -0.06
     Shipping
    -0.06
     Knox
    -0.06
     neon
    -0.05
     Build
    -0.05
    æk
    -0.05
    semicolon
    -0.05
     relocate
    -0.05
    literal
    -0.05
     traction
    -0.05
    POSITIVE LOGITS
     Cinder
    0.09
     disguised
    0.09
     disguise
    0.09
     court
    0.08
     princ
    0.08
     Prince
    0.08
     Ballet
    0.08
     Al
    0.08
     Court
    0.08
     disgu
    0.08
    Activations Density 0.003%

    No Known Activations