© 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. 15-LLAMASCOPE-RES-131K
    11. 86178
    Prev
    Next
    INDEX
    Explanations

    references to specific meetings or formal gatherings

    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
     setC
    -0.07
    oÅĻ
    -0.07
    angen
    -0.07
    éf
    -0.07
    eft
    -0.07
    _detach
    -0.07
    elease
    -0.07
    ãĥIJãĤ¤
    -0.06
    MED
    -0.06
    eat
    -0.06
    POSITIVE LOGITS
    inqu
    0.07
     recently
    0.06
     Nicholson
    0.06
    asaki
    0.06
    enties
    0.06
    oir
    0.06
    ADDR
    0.06
    cko
    0.06
     Druh
    0.06
    acier
    0.06
    Activations Density 0.023%

    No Known Activations