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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-LLAMASCOPE-RES-131K
    6. 4460
    Prev
    Next
    INDEX
    Explanations

    references to Walmart and related contextual phrases

    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
    íĽĦ
    -0.07
    erb
    -0.07
    cept
    -0.07
     sklad
    -0.07
     cara
    -0.07
    andes
    -0.07
    ment
    -0.07
    steder
    -0.06
    帯
    -0.06
    lle
    -0.06
    POSITIVE LOGITS
    rus
    0.09
    nuts
    0.08
    greens
    0.08
    loon
    0.08
    nut
    0.07
    tec
    0.07
    ther
    0.07
    -Mart
    0.07
     Mart
    0.07
    entine
    0.07
    Activations Density 0.005%

    No Known Activations