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. 9-LLAMASCOPE-RES-131K
    6. 96125
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating pauses and sentence structure

    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
    	Copyright
    -0.08
    ERRU
    -0.07
    908
    -0.07
     ëĦ¤ìĿ´íĬ¸
    -0.07
    itzer
    -0.07
    .ends
    -0.07
    ãģ»ãģ©
    -0.07
    ØŃÙĩ
    -0.07
    ãĤ¢ãĥ³
    -0.07
    POWER
    -0.07
    POSITIVE LOGITS
    abay
    0.07
    ildo
    0.07
    indr
    0.07
     then
    0.06
    ubl
    0.06
     Dank
    0.06
     Unknown
    0.06
     Reviews
    0.06
    reno
    0.06
    Unnamed
    0.06
    Activations Density 0.099%

    No Known Activations