© 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. 14173
    Prev
    Next
    INDEX
    Explanations

    instances of the word "appeared."

    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
    utz
    -0.06
    æ¸Ī
    -0.06
    @(
    -0.06
     Vys
    -0.06
    ован
    -0.06
    ARSE
    -0.06
    locator
    -0.06
    -0.06
    excel
    -0.06
    yz
    -0.06
    POSITIVE LOGITS
    urat
    0.07
    affer
    0.06
    िथ
    0.06
    ubu
    0.06
    UNT
    0.06
    udu
    0.06
    arsers
    0.06
    inders
    0.06
    avier
    0.06
    aleigh
    0.06
    Activations Density 0.000%

    No Known Activations