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. 43754
    Prev
    Next
    INDEX
    Explanations

    mathematical notations or symbols related to functions and variables

    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
     acess
    -0.07
     acces
    -0.06
    ENAME
    -0.06
    akis
    -0.06
     pupils
    -0.06
     prive
    -0.05
     tumblr
    -0.05
    /trunk
    -0.05
    nof
    -0.05
    :frame
    -0.05
    POSITIVE LOGITS
     ANSI
    0.11
     IEEE
    0.10
     ASTM
    0.10
     manufacturer
    0.10
     manufacturers
    0.10
     ISO
    0.10
     engineers
    0.10
     Manufacturers
    0.09
     OEM
    0.09
     engineer
    0.09
    Activations Density 0.006%

    No Known Activations