© 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. 124127
    Prev
    Next
    INDEX
    Explanations

    topics related to social infrastructure and funding challenges

    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
    ille
    -0.07
    ETO
    -0.07
    ulla
    -0.07
     bindActionCreators
    -0.07
    WER
    -0.06
    omore
    -0.06
    otal
    -0.06
     pard
    -0.06
    /media
    -0.06
    rypton
    -0.06
    POSITIVE LOGITS
     services
    0.11
     programs
    0.11
     Services
    0.09
     programmes
    0.09
    Services
    0.09
     public
    0.08
     Programs
    0.08
    services
    0.08
     service
    0.08
    -services
    0.08
    Activations Density 0.027%

    No Known Activations