Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-LLAMASCOPE-RES-131K
    6. 96079
    Prev
    Next
    INDEX
    Explanations

    references to bathrooms and their features in a property description

    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
    ãĥ£
    -0.08
    berger
    -0.07
    ία
    -0.06
    ually
    -0.06
    enthal
    -0.06
     Pill
    -0.06
    sd
    -0.06
    unas
    -0.06
    shirt
    -0.06
    burger
    -0.05
    POSITIVE LOGITS
    ynamo
    0.09
    .Dispatcher
    0.07
     den
    0.07
    erot
    0.07
    uda
    0.07
    vnÃŃ
    0.06
    jišť
    0.06
     Hell
    0.06
    illance
    0.06
    enville
    0.06
    Activations Density 0.002%

    No Known Activations