© 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. 81840
    Prev
    Next
    INDEX
    Explanations

    references to legal or government actions

    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
    mal
    -0.07
     unfortunately
    -0.07
     sadly
    -0.06
    enna
    -0.06
    _Master
    -0.06
    666
    -0.06
    enant
    -0.06
    ŃIJï¸ı
    -0.06
     Frag
    -0.06
    olith
    -0.06
    POSITIVE LOGITS
     eventually
    0.16
    Eventually
    0.14
     Eventually
    0.14
     eventual
    0.14
     ultimately
    0.13
     Ultimately
    0.10
     finally
    0.10
    Ultimately
    0.10
     ultimate
    0.09
     resolution
    0.09
    Activations Density 0.064%

    No Known Activations