© 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. 54075
    Prev
    Next
    INDEX
    Explanations

    variations of the word "shred" and its derivatives

    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
    467
    -0.06
    uate
    -0.06
    esimal
    -0.06
    ee
    -0.06
    orate
    -0.06
    amd
    -0.06
     Directions
    -0.06
    fried
    -0.06
    pla
    -0.06
    _raise
    -0.05
    POSITIVE LOGITS
    stakes
    0.09
    leston
    0.09
    ijk
    0.08
    RESP
    0.07
    lings
    0.07
    ospel
    0.07
    ombat
    0.07
    inke
    0.07
    nodoc
    0.07
    Thrown
    0.07
    Activations Density 0.001%

    No Known Activations