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. 44058
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols, possibly in the context of programming or mathematical expressions

    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
     JetBrains
    -0.07
    ismet
    -0.07
    ãĥīãĥ«
    -0.06
    iglia
    -0.06
    (DataType
    -0.06
    eldorf
    -0.06
    atown
    -0.06
    apon
    -0.06
     USDA
    -0.06
    :↵
    -0.06
    POSITIVE LOGITS
     Kenya
    0.18
     Ken
    0.15
     Nairobi
    0.15
    Ken
    0.14
     Uganda
    0.13
    KEN
    0.11
     Tanzania
    0.11
     ken
    0.11
    ken
    0.10
     Kis
    0.10
    Activations Density 0.004%

    No Known Activations