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. 5591
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and logical expressions

    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
    cheon
    -0.06
    ToLocal
    -0.06
    idal
    -0.06
    amil
    -0.06
    errat
    -0.06
    enas
    -0.06
    ấc
    -0.06
    ÑĤик
    -0.06
    chang
    -0.06
    Ãĭ
    -0.06
    POSITIVE LOGITS
     another
    0.08
     Another
    0.07
     Others
    0.07
     others
    0.07
    ulumi
    0.06
     nhau
    0.06
    ERE
    0.06
    ucci
    0.06
    vey
    0.06
     Sanct
    0.06
    Activations Density 0.057%

    No Known Activations