© 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. 104246
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and reference details in scientific literature

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ủ
    -0.07
    ruc
    -0.07
    İ·
    -0.06
    á»į
    -0.06
    ÃŃÅ¡
    -0.06
    lotte
    -0.06
    baÅŁ
    -0.06
    rowse
    -0.06
    enk
    -0.06
    ÑģÑĸм
    -0.06
    POSITIVE LOGITS
    werk
    0.06
    ĽĦ
    0.06
     comm
    0.06
    ene
    0.06
    еÑĢк
    0.06
     Leonard
    0.06
     EQ
    0.06
    653
    0.05
     Neon
    0.05
    θε
    0.05
    Activations Density 0.009%

    No Known Activations