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. 44201
    Prev
    Next
    INDEX
    Explanations

    various mathematical and statistical symbols and terms

    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
    orthand
    -0.08
     JMP
    -0.07
    аÑĤо
    -0.07
     Bronx
    -0.07
     Perth
    -0.07
    ubar
    -0.06
     Pav
    -0.06
     Giang
    -0.06
    gorithm
    -0.06
     Cupertino
    -0.06
    POSITIVE LOGITS
     Titans
    0.23
     Tennessee
    0.23
     Nashville
    0.19
     Titan
    0.18
    Tit
    0.18
     Tenn
    0.17
     TN
    0.15
     tit
    0.15
     Tit
    0.15
     Knoxville
    0.14
    Activations Density 0.005%

    No Known Activations