© 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. 42819
    Prev
    Next
    INDEX
    Explanations

    references to memoirs and personal narratives

    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
     currently
    -0.08
    currently
    -0.07
    irut
    -0.07
     presently
    -0.06
    itech
    -0.06
    ozy
    -0.06
    /tos
    -0.06
    pt
    -0.06
    emit
    -0.06
     Treaty
    -0.06
    POSITIVE LOGITS
     usually
    0.13
     often
    0.12
    Usually
    0.12
    usually
    0.12
     Usually
    0.11
     tend
    0.11
    often
    0.10
     always
    0.10
     obvykle
    0.10
     tends
    0.10
    Activations Density 0.046%

    No Known Activations