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. 5768
    Prev
    Next
    INDEX
    Explanations

    references to relationships and personal connections

    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
     Karma
    -0.07
    opus
    -0.07
    å¼Ł
    -0.06
    suma
    -0.06
    oint
    -0.06
     Kop
    -0.06
     Directorate
    -0.06
    /tiny
    -0.06
     funk
    -0.06
    serter
    -0.06
    POSITIVE LOGITS
     Gone
    0.11
     plantation
    0.08
    pth
    0.07
    ANNOT
    0.07
    Wind
    0.07
     gone
    0.07
     Wind
    0.07
     ë°ĶëŀĮ
    0.07
     wind
    0.07
    bersome
    0.07
    Activations Density 0.004%

    No Known Activations