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

    Neuronpedia

    APICircuit 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. MLP Out
    5. 29-LLAMASCOPE-MLP-131K
    6. 5083
    Prev
    Next
    INDEX
    Explanations

    phrases indicating assistance and guidance in addressing social issues

    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
    wald
    -0.07
    ashi
    -0.07
    .run
    -0.07
     Ran
    -0.06
    ÑĢаÐ
    -0.06
    run
    -0.06
    acre
    -0.06
    _Run
    -0.06
    aju
    -0.06
     ran
    -0.06
    POSITIVE LOGITS
     n
    0.07
     end
    0.07
     side
    0.06
     straight
    0.06
     at
    0.06
    (LogLevel
    0.06
     level
    0.06
    /hash
    0.06
     even
    0.06
    rescia
    0.06
    Activations Density 0.032%

    No Known Activations