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. 5584
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ettle
    -0.06
     fortn
    -0.06
    ovenant
    -0.06
    eldon
    -0.06
    ln
    -0.06
    ure
    -0.06
     massively
    -0.06
    aho
    -0.06
     &
    -0.06
    anko
    -0.05
    POSITIVE LOGITS
    åľŃ
    0.07
     ÑģÑĤаÑĤи
    0.07
    bersome
    0.07
     اÙĦرÙħزÙĬØ©
    0.07
    eway
    0.07
    çĦ¡ãģĹãģ
    0.07
    ï¼Īç¬ij
    0.06
    Wunused
    0.06
    ãĥ»ãĥ»ãĥ»↵↵
    0.06
     meiner
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.