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. 44235
    Prev
    Next
    INDEX
    Explanations

    occurrences of shopping and retail-related terms

    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
    é«ĺæ¸ħ
    -0.07
    rzy
    -0.07
    .rpm
    -0.07
    ifecycle
    -0.07
    /site
    -0.07
    Cancelled
    -0.06
    cancelled
    -0.06
    ãĥªãĥ³
    -0.06
    ãģ«ãģĭ
    -0.06
    ãĥĢãĥ¼
    -0.06
    POSITIVE LOGITS
     Watson
    0.10
     Lawson
    0.09
     Guardian
    0.09
     hyper
    0.08
     Mustafa
    0.08
     outlets
    0.08
     Hyper
    0.08
     AE
    0.07
     department
    0.07
     outlet
    0.07
    Activations Density 0.015%

    No Known Activations