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. 43985
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical issues or errors, particularly in software 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
    FTP
    -0.09
     ftp
    -0.09
    ftp
    -0.08
     Winchester
    -0.08
     Aberdeen
    -0.07
     FTP
    -0.07
    igua
    -0.07
     Ebola
    -0.07
     Benghazi
    -0.07
    .azure
    -0.07
    POSITIVE LOGITS
     Pixel
    0.28
    Pixel
    0.23
     Pixels
    0.22
     Google
    0.21
    .Pixel
    0.18
     pixel
    0.18
     PIXEL
    0.18
    Google
    0.17
     GOOGLE
    0.17
     google
    0.16
    Activations Density 0.007%

    No Known Activations