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. 43748
    Prev
    Next
    INDEX
    Explanations

    unicode characters or special symbols

    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
    3
    -0.07
    2
    -0.06
    1
    -0.06
    24
    -0.06
    365
    -0.06
    10
    -0.06
    4
    -0.06
    -scalable
    -0.06
     [â̦]↵↵
    -0.05
    7
    -0.05
    POSITIVE LOGITS
     vs
    0.08
     distribution
    0.08
    ,
    0.08
     Distribution
    0.07
     forecast
    0.07
     compared
    0.07
     by
    0.07
    distribution
    0.07
     versus
    0.07
     semester
    0.07
    Activations Density 0.003%

    No Known Activations