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. 43899
    Prev
    Next
    INDEX
    Explanations

    specific characters or symbols that signal non-standard or coded text

    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
     Retail
    -0.06
     Spicer
    -0.06
    Retail
    -0.06
    ecial
    -0.06
    ãĥªãĤ«
    -0.06
    _vendor
    -0.05
     retailer
    -0.05
    oplayer
    -0.05
    blk
    -0.05
    odia
    -0.05
    POSITIVE LOGITS
     Couch
    0.24
     couch
    0.22
     hosts
    0.14
     sofa
    0.13
     host
    0.13
     sofas
    0.12
     Sofa
    0.12
     Host
    0.12
     hostel
    0.12
    hosts
    0.12
    Activations Density 0.005%

    No Known Activations