© 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. 116572
    Prev
    Next
    INDEX
    Explanations

    terms related to the beginning and end of processes or events

    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
    imb
    -0.08
    ucci
    -0.07
    izable
    -0.07
    arken
    -0.06
    ester
    -0.06
    opoulos
    -0.06
     tai
    -0.06
     è²
    -0.06
     Tai
    -0.06
    °
    -0.06
    POSITIVE LOGITS
    -dat
    0.08
    edException
    0.07
    itzer
    0.07
    WebResponse
    0.07
    ãĥ¥ãĥ¼
    0.07
    579
    0.07
    AINS
    0.07
    usercontent
    0.07
    flater
    0.07
    Reached
    0.07
    Activations Density 0.018%

    No Known Activations