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. 43502
    Prev
    Next
    INDEX
    Explanations

    names of people and pets

    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
    outu
    -0.08
    useum
    -0.08
    alleries
    -0.08
    outers
    -0.08
    appers
    -0.07
    ispers
    -0.07
    allery
    -0.07
     Mrs
    -0.07
    iciary
    -0.07
    okies
    -0.07
    POSITIVE LOGITS
    lee
    0.11
     whom
    0.11
    lyn
    0.10
     Jr
    0.10
     born
    0.10
     who
    0.10
     age
    0.10
     aged
    0.09
     Rae
    0.09
    Lee
    0.09
    Activations Density 0.049%

    No Known Activations