© 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. 9-LLAMASCOPE-RES-131K
    11. 94137
    Prev
    Next
    INDEX
    Explanations

    the word "This" and its variations, indicating a focus on demonstrative pronouns

    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
    our
    -0.07
    ave
    -0.07
    tings
    -0.07
    entimes
    -0.06
    ed
    -0.06
    iny
    -0.06
    ASA
    -0.06
    ish
    -0.06
    63
    -0.06
    нак
    -0.06
    POSITIVE LOGITS
    oretical
    0.08
    CLUDING
    0.08
    ptal
    0.07
    riz
    0.07
    .nih
    0.07
    keit
    0.07
    êu
    0.07
    à¹Ģà¸Ńà¸ĩ
    0.07
     تب
    0.07
    kiye
    0.07
    Activations Density 0.089%

    No Known Activations