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. 44232
    Prev
    Next
    INDEX
    Explanations

    references and citation formats

    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
    ãĥ¥ãĥ¼
    -0.09
     Tweets
    -0.08
    .posts
    -0.08
     Blogs
    -0.07
     dosud
    -0.07
    ews
    -0.07
    meldung
    -0.07
     má»Ŀi
    -0.07
    blogs
    -0.07
     banka
    -0.07
    POSITIVE LOGITS
     page
    0.21
     p
    0.20
     pg
    0.20
     pp
    0.20
     pages
    0.18
     Pg
    0.17
     Page
    0.15
     chapter
    0.14
     pag
    0.14
    pp
    0.14
    Activations Density 0.389%

    No Known Activations