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. 44146
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical tours and community experiences

    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
    ainter
    -0.07
     CONTRIBUTORS
    -0.07
    SPA
    -0.07
    TAIL
    -0.07
     ÙĩÙĨر
    -0.07
    anco
    -0.07
    631
    -0.07
    alars
    -0.07
    Animating
    -0.07
    _PI
    -0.06
    POSITIVE LOGITS
     Mitch
    0.09
     Mitchell
    0.09
     informal
    0.08
     Kh
    0.08
     Phil
    0.08
     Wyn
    0.08
     Ny
    0.07
     Ocean
    0.07
     Ath
    0.07
     Sea
    0.07
    Activations Density 0.007%

    No Known Activations