© 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. 31619
    Prev
    Next
    INDEX
    Explanations

    references to note-taking and related tools or services

    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
    uben
    -0.07
    _initialize
    -0.06
    iland
    -0.06
    _locals
    -0.06
    æ½
    -0.06
    è³Ģ
    -0.06
     hob
    -0.06
     Ñģб
    -0.06
     cocks
    -0.06
    ufen
    -0.06
    POSITIVE LOGITS
     occas
    0.08
     frequently
    0.07
     often
    0.07
     frequent
    0.07
    iel
    0.07
    often
    0.06
     serm
    0.06
    ambi
    0.06
     regularly
    0.06
    conte
    0.06
    Activations Density 0.026%

    No Known Activations