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. 44030
    Prev
    Next
    INDEX
    Explanations

    technical references and specific parameters related to programming or web development

    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
    DisplayStyle
    -0.07
    CHANT
    -0.06
    ffset
    -0.06
     Colbert
    -0.06
    caster
    -0.06
     XHTML
    -0.06
    aoke
    -0.06
    =wx
    -0.06
    olarity
    -0.06
    адж
    -0.06
    POSITIVE LOGITS
     Lambda
    0.23
     lambda
    0.21
    Lambda
    0.20
    lambda
    0.18
    _lambda
    0.18
     Lamb
    0.18
    .lambda
    0.18
    (lambda
    0.17
     lamb
    0.17
     AWS
    0.15
    Activations Density 0.013%

    No Known Activations