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. 43681
    Prev
    Next
    INDEX
    Explanations

    specific dates and record identifiers in official documents

    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
     necessary
    -0.06
     required
    -0.06
     weekly
    -0.05
     necessities
    -0.05
     Engineers
    -0.05
     needed
    -0.05
     traditional
    -0.05
     popular
    -0.05
    onya
    -0.05
     instead
    -0.05
    POSITIVE LOGITS
     method
    0.14
     methods
    0.14
     Method
    0.14
     METHOD
    0.14
     Methods
    0.13
    æĸ¹æ³ķ
    0.13
    Method
    0.12
     apparatus
    0.12
    method
    0.12
     METHODS
    0.12
    Activations Density 0.255%

    No Known Activations