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. 11511
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or entities

    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
     Catalan
    -0.08
    rsa
    -0.07
    enek
    -0.07
     GSL
    -0.07
     Mexican
    -0.07
    _RSA
    -0.07
    ález
    -0.07
    ÏĦοÏį
    -0.07
    idx
    -0.07
    ulg
    -0.07
    POSITIVE LOGITS
     Lima
    0.13
     Lamb
    0.12
     Peru
    0.12
     Hu
    0.12
     peru
    0.11
    Hu
    0.10
     Call
    0.09
     Anc
    0.09
     Pi
    0.09
     Per
    0.09
    Activations Density 0.005%

    No Known Activations