© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 69202
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to mathematical functions and mappings

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    fty
    -0.07
    imus
    -0.06
    hic
    -0.06
    rus
    -0.06
     run
    -0.06
    à¸´à¸Ľ
    -0.06
    iya
    -0.06
    -run
    -0.06
    enheim
    -0.06
    ickle
    -0.06
    POSITIVE LOGITS
     formed
    0.10
     obtained
    0.09
     пÑĥÑĤем
    0.09
     ÑĪлÑıÑħом
    0.09
    formed
    0.09
     formation
    0.08
     simply
    0.08
     indem
    0.07
     Formation
    0.07
     created
    0.07
    Activations Density 0.163%

    No Known Activations