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. 43413
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate provision or allocation of resources or assistance

    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
    ology
    -0.08
    ordinary
    -0.07
    кÑĥÑĢ
    -0.07
    forman
    -0.07
    dül
    -0.07
    pedia
    -0.07
    irror
    -0.07
    дам
    -0.07
    olution
    -0.07
    town
    -0.07
    POSITIVE LOGITS
     least
    0.19
     Least
    0.12
     lest
    0.12
    _least
    0.11
     lease
    0.10
    Least
    0.10
     minimum
    0.10
     LE
    0.10
     most
    0.10
    -le
    0.10
    Activations Density 0.010%

    No Known Activations