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. 22-LLAMASCOPE-RES-131K
    6. 5470
    Prev
    Next
    INDEX
    Explanations

    structured data representations or definitions

    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
     [](
    -0.07
    ands
    -0.07
    dál
    -0.06
    orie
    -0.06
    asca
    -0.06
    رخ
    -0.06
    rowning
    -0.06
    <>(
    -0.06
    anager
    -0.06
    leased
    -0.06
    POSITIVE LOGITS
     string
    0.12
     number
    0.10
    string
    0.10
    number
    0.09
     boolean
    0.09
     Pick
    0.09
     Partial
    0.09
     any
    0.09
     Record
    0.08
     typeof
    0.08
    Activations Density 0.002%

    No Known Activations