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. 43823
    Prev
    Next
    INDEX
    Explanations

    specific numeric or statistical data related to various topics

    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
    abox
    -0.06
    ~-~-~-~-
    -0.06
    eri
    -0.06
    ogl
    -0.06
    htar
    -0.06
    Faces
    -0.06
     karak
    -0.06
    ithub
    -0.06
     samo
    -0.06
    æķ¬
    -0.06
    POSITIVE LOGITS
     pic
    0.13
     picture
    0.13
     photograph
    0.11
     photo
    0.11
     snapshot
    0.11
     image
    0.11
    pic
    0.09
     Pic
    0.09
    .jpg
    0.09
     Furniture
    0.09
    Activations Density 0.002%

    No Known Activations