© 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. 1432
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "song" and its variations in context

    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
    ustralian
    -0.07
    uning
    -0.07
    ustral
    -0.07
    connector
    -0.07
    sed
    -0.07
    ted
    -0.07
    ãģĬãĤĬ
    -0.06
    tings
    -0.06
     вÑģего
    -0.06
    /student
    -0.06
    POSITIVE LOGITS
    stress
    0.12
    writing
    0.11
    writers
    0.10
    bird
    0.08
    smith
    0.08
    birds
    0.08
    ê³³
    0.08
    /videos
    0.08
    ularity
    0.08
    writer
    0.08
    Activations Density 0.022%

    No Known Activations