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. 43421
    Prev
    Next
    INDEX
    Explanations

    elements related to a technical or mathematical context, especially involving equations and parameters

    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
    abies
    -0.06
     hockey
    -0.06
    gang
    -0.06
     sounding
    -0.05
     Duy
    -0.05
    anga
    -0.05
    ัà¸ĩ
    -0.05
     insign
    -0.05
    олиÑĤ
    -0.05
     rowspan
    -0.05
    POSITIVE LOGITS
     catcher
    0.10
     error
    0.09
     throwing
    0.09
    throw
    0.09
     interception
    0.09
     Error
    0.08
     errors
    0.08
     pitcher
    0.08
    LOB
    0.08
     infield
    0.08
    Activations Density 0.003%

    No Known Activations