© 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. 116741
    Prev
    Next
    INDEX
    Explanations

    variations of the sub-word "ano."

    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
    uten
    -0.08
    brick
    -0.08
    ulaire
    -0.08
    iedad
    -0.07
    rieving
    -0.07
    pering
    -0.07
    opus
    -0.07
    otland
    -0.07
    lassian
    -0.07
    olly
    -0.07
    POSITIVE LOGITS
    ymous
    0.08
    VB
    0.07
    an
    0.07
    orz
    0.07
    isseur
    0.06
    ysz
    0.06
    el
    0.06
    ingly
    0.06
     Äijó
    0.06
    ëŀĺ
    0.06
    Activations Density 0.022%

    No Known Activations