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. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43651
    Prev
    Next
    INDEX
    Explanations

    mentions of music and its quality in relation to films

    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
    acos
    -0.07
    ارس
    -0.06
     booking
    -0.06
     touring
    -0.06
    BCM
    -0.06
    å·¡
    -0.06
    commission
    -0.06
     commission
    -0.06
    atform
    -0.06
     Tokyo
    -0.06
    POSITIVE LOGITS
     rend
    0.09
     rendering
    0.09
     rendered
    0.09
     render
    0.09
    render
    0.08
     gh
    0.08
     recreated
    0.08
     rendition
    0.08
     melod
    0.08
     humming
    0.08
    Activations Density 0.006%

    No Known Activations