© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77078
    Prev
    Next
    INDEX
    Explanations

    phrases related to retail and specialty stores

    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
     hospitals
    -0.07
     Hospitals
    -0.06
     restaurants
    -0.06
     hotels
    -0.06
     reverse
    -0.06
     round
    -0.06
     rules
    -0.06
     Vine
    -0.05
     McDonald
    -0.05
    ServiceProvider
    -0.05
    POSITIVE LOGITS
    488
    0.08
    agner
    0.07
    å°¿
    0.07
    ystore
    0.07
    edik
    0.07
    /antlr
    0.07
     assort
    0.07
    -store
    0.07
     Ùħتخصص
    0.07
     store
    0.07
    Activations Density 0.026%

    No Known Activations