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. 43427
    Prev
    Next
    INDEX
    Explanations

    aspects of culinary experiences or food-related components

    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
     Eston
    -0.08
     Estonia
    -0.07
     Maced
    -0.07
     Angola
    -0.07
     Ars
    -0.07
    bens
    -0.07
     Pessoa
    -0.07
    ıb
    -0.07
     Macedonia
    -0.07
     McInt
    -0.06
    POSITIVE LOGITS
     marg
    0.14
     Tex
    0.13
     Marg
    0.13
     Cin
    0.13
     ta
    0.13
     mari
    0.13
     tort
    0.13
     Ta
    0.12
     fi
    0.11
     Mari
    0.11
    Activations Density 0.026%

    No Known Activations