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. 25-LLAMASCOPE-MLP-131K
    6. 72555
    Prev
    Next
    INDEX
    Explanations

    numerical values and indicators of order or ranking

    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
    ạn
    -0.07
     ì¶ľìŀ¥
    -0.06
    thinkable
    -0.06
    Unhandled
    -0.06
    eref
    -0.06
    OffsetTable
    -0.06
     Erotische
    -0.06
     нег
    -0.06
    одо
    -0.06
     Osman
    -0.06
    POSITIVE LOGITS
    omba
    0.07
    liner
    0.06
    lice
    0.06
    esti
    0.06
    oni
    0.06
    ahr
    0.06
    inis
    0.06
    larla
    0.06
    down
    0.06
    oo
    0.06
    Activations Density 0.002%

    No Known Activations