© 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. 91788
    Prev
    Next
    INDEX
    Explanations

    the terms and structures related to comparison and analysis in procedural or algorithmic contexts

    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
    quirer
    -0.07
    GestureRecognizer
    -0.07
    Äĥn
    -0.07
    essler
    -0.06
    eer
    -0.06
    .ibm
    -0.06
    ạ
    -0.06
    PÅĻi
    -0.06
    ibo
    -0.06
    inya
    -0.06
    POSITIVE LOGITS
     #
    0.10
    #
    0.07
     #↵
    0.06
    (#)
    0.06
    thalm
    0.06
    itol
    0.06
    âijł
    0.06
    -hours
    0.06
    #![
    0.06
     #$
    0.06
    Activations Density 0.107%

    No Known Activations