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. 22-LLAMASCOPE-RES-131K
    6. 5495
    Prev
    Next
    INDEX
    Explanations

    references to audience engagement and viewership statistics

    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
    è£
    -0.07
    ÐIJÑĢÑħÑĸв
    -0.07
    oppins
    -0.07
    zych
    -0.07
    Ø¡
    -0.06
    okit
    -0.06
    ière
    -0.06
    -panel
    -0.06
    mojom
    -0.06
    411
    -0.06
    POSITIVE LOGITS
    raq
    0.06
     αÏģι
    0.06
     thousands
    0.06
     hundreds
    0.06
    eral
    0.06
     tens
    0.06
    ableView
    0.06
     Cous
    0.06
    oked
    0.06
     nearly
    0.06
    Activations Density 0.006%

    No Known Activations