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. 11538
    Prev
    Next
    INDEX
    Explanations

    references to courier services and delivery details

    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
    SOLE
    -0.07
    ubo
    -0.06
    abler
    -0.06
    sanitize
    -0.06
    enso
    -0.06
    irse
    -0.06
    uala
    -0.06
    ست
    -0.06
    scan
    -0.06
    akeup
    -0.06
    POSITIVE LOGITS
     Smith
    0.61
    Smith
    0.52
     smith
    0.47
    -Smith
    0.43
    smith
    0.40
     SM
    0.35
    .sm
    0.30
    -sm
    0.29
    _sm
    0.28
    mith
    0.27
    Activations Density 0.042%

    No Known Activations