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. 43900
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly exclamation points and periods

    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
     certainly
    -0.09
    OrElse
    -0.08
     Certainly
    -0.08
    ccione
    -0.08
    quent
    -0.08
    ëĶĶìĭľ
    -0.08
    <quote
    -0.07
    realDonaldTrump
    -0.07
    nech
    -0.07
     putas
    -0.07
    POSITIVE LOGITS
    {
    0.08
     {
    0.07
     fabric
    0.07
    {{{
    0.07
    ps
    0.07
    ...
    0.07
    **
    0.07
    such
    0.06
    1
    0.06
    Âł
    0.06
    Activations Density 0.023%

    No Known Activations