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. 44046
    Prev
    Next
    INDEX
    Explanations

    instances of the term "se" in various contexts

    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
    g
    -0.09
    al
    -0.09
    c
    -0.09
    znam
    -0.09
    e
    -0.08
    sWith
    -0.08
    aliz
    -0.08
    inem
    -0.07
    at
    -0.07
    kova
    -0.07
    POSITIVE LOGITS
    cession
    0.10
    ptic
    0.10
    cur
    0.10
    eder
    0.09
    crete
    0.09
    attle
    0.09
    bastian
    0.08
    quest
    0.08
    ced
    0.08
    pare
    0.08
    Activations Density 0.007%

    No Known Activations