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. 44228
    Prev
    Next
    INDEX
    Explanations

    geographic locations or names of places

    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
     å¾ĴæŃ©
    -0.08
    @nate
    -0.08
    amarin
    -0.07
    olib
    -0.07
    виÑĩ
    -0.07
    ascus
    -0.07
    _repr
    -0.07
    quip
    -0.07
     lucr
    -0.07
    iferay
    -0.06
    POSITIVE LOGITS
     branch
    0.13
     portion
    0.11
     chapter
    0.11
     section
    0.10
     region
    0.10
    -based
    0.10
     office
    0.09
     area
    0.09
     campus
    0.09
     equivalent
    0.09
    Activations Density 0.088%

    No Known Activations