© 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. 69060
    Prev
    Next
    INDEX
    Explanations

    numerical data and file references related to research studies

    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
    еÑĢ
    -0.07
    bn
    -0.06
    shaw
    -0.06
     –
    -0.06
     kne
    -0.06
     De
    -0.06
    als
    -0.06
     Raven
    -0.05
    benh
    -0.05
    ammable
    -0.05
    POSITIVE LOGITS
    ãĤ¤ãĥ³ãĥĪ
    0.08
     tabla
    0.07
    WORDS
    0.07
    <size
    0.07
    .MenuStrip
    0.07
    icas
    0.07
     ÑĢазмеÑĢ
    0.07
    ãĤµãĤ¤ãĤº
    0.07
    ivre
    0.07
    ambil
    0.07
    Activations Density 0.003%

    No Known Activations