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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 87454
    Prev
    Next
    INDEX
    Explanations

    phrases related to user-friendliness and accessibility in technology

    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
    isko
    -0.06
    æĺŃ
    -0.06
    isl
    -0.06
    uentes
    -0.06
    aul
    -0.06
     once
    -0.06
    ildo
    -0.05
    é¼»
    -0.05
     casting
    -0.05
     aw
    -0.05
    POSITIVE LOGITS
    :max
    0.08
     specifically
    0.08
    |max
    0.08
     Specifically
    0.08
    specific
    0.07
     maximum
    0.07
     nên
    0.07
     specific
    0.07
     convenience
    0.07
    mür
    0.07
    Activations Density 0.032%

    No Known Activations