© 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. 89426
    Prev
    Next
    INDEX
    Explanations

    references to data handling and reporting processes within technological contexts

    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
    generic
    -0.07
     Meg
    -0.06
    æī§
    -0.06
    Meg
    -0.06
    ATAL
    -0.06
    ximity
    -0.06
    TRACE
    -0.05
    source
    -0.05
     Gad
    -0.05
    vn
    -0.05
    POSITIVE LOGITS
     reporting
    0.13
     report
    0.12
     send
    0.12
    send
    0.12
     submission
    0.12
    report
    0.11
     sending
    0.11
     Reporting
    0.11
     submitting
    0.11
     Send
    0.11
    Activations Density 0.060%

    No Known Activations