© 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. 38397
    Prev
    Next
    INDEX
    Explanations

    instances of the word "together" or phrases emphasizing collaboration and unity

    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
    ysi
    -0.10
    .FontStyle
    -0.09
    outu
    -0.09
    iras
    -0.08
    apeut
    -0.08
    kea
    -0.08
    etur
    -0.07
    jen
    -0.07
    .builders
    -0.07
    íĤ¹
    -0.07
    POSITIVE LOGITS
     these
    0.12
     together
    0.09
    è¿ĻäºĽ
    0.08
     These
    0.08
    these
    0.08
     Together
    0.08
    These
    0.07
    Together
    0.07
     across
    0.07
     ÑįÑĤиÑħ
    0.07
    Activations Density 0.009%

    No Known Activations