© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 95593
    Prev
    Next
    INDEX
    Explanations

    references to research findings and evaluations, particularly those concerning public health programs

    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
    ENDOR
    -0.07
    à¸Ļม
    -0.06
     correctly
    -0.06
    боÑĤ
    -0.06
     deserted
    -0.05
    isko
    -0.05
    endale
    -0.05
    utos
    -0.05
     topp
    -0.05
    ÑĢоÑģ
    -0.05
    POSITIVE LOGITS
     publication
    0.12
     report
    0.11
    publication
    0.11
    .public
    0.11
     publish
    0.10
     public
    0.10
     publications
    0.10
     пÑĥблÑĸ
    0.09
    -public
    0.09
    public
    0.09
    Activations Density 0.021%

    No Known Activations