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. 43568
    Prev
    Next
    INDEX
    Explanations

    technical programming terms related to graphics rendering

    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
    ÑĭÑģ
    -0.06
     Norse
    -0.06
     اÙĦÙĨÙĪ
    -0.06
    OnInit
    -0.05
     diameter
    -0.05
     Yak
    -0.05
     Nach
    -0.05
     gap
    -0.05
    stras
    -0.05
    Ùĩد
    -0.05
    POSITIVE LOGITS
    Blend
    0.14
     Blend
    0.14
    _blend
    0.13
    blend
    0.13
     Alpha
    0.12
    Alpha
    0.12
    _BLEND
    0.12
     Src
    0.12
     alpha
    0.11
     blend
    0.11
    Activations Density 0.046%

    No Known Activations