© 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. 121365
    Prev
    Next
    INDEX
    Explanations

    instances of significant numeric or structural elements in the text

    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
    ONGL
    -0.08
    ILA
    -0.07
    ĵåIJį
    -0.07
    ungeons
    -0.07
    pty
    -0.07
    ovny
    -0.07
    oulos
    -0.06
    abor
    -0.06
    enga
    -0.06
    ADDE
    -0.06
    POSITIVE LOGITS
    ppe
    0.07
    overe
    0.07
    iton
    0.06
     Gos
    0.06
     Care
    0.06
     hum
    0.05
    riel
    0.05
     пеÑĢеп
    0.05
    ìŀ
    0.05
    allery
    0.05
    Activations Density 0.000%

    No Known Activations