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. 43841
    Prev
    Next
    INDEX
    Explanations

    terms related to availability and service offerings

    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
    THEN
    -0.09
     THEN
    -0.08
    ptime
    -0.07
    ãĢĤãģĿãģĹãģ¦
    -0.07
    \Common
    -0.06
    λÏħ
    -0.06
    oge
    -0.06
    Ù쨩
    -0.06
    prite
    -0.06
    Then
    -0.06
    POSITIVE LOGITS
     upon
    0.19
    upon
    0.15
     subject
    0.15
     Upon
    0.14
    Upon
    0.12
     contact
    0.12
     if
    0.11
    subject
    0.11
     Contact
    0.10
    (subject
    0.10
    Activations Density 0.054%

    No Known Activations