© 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. 117758
    Prev
    Next
    INDEX
    Explanations

    diverse food options and culinary variety

    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
     reform
    -0.06
    ide
    -0.06
    ung
    -0.06
    ngo
    -0.06
    alar
    -0.06
    eno
    -0.06
    _RESERVED
    -0.06
     big
    -0.06
    yc
    -0.05
     Q
    -0.05
    POSITIVE LOGITS
     colors
    0.08
    acam
    0.08
     types
    0.07
     colours
    0.07
     kinds
    0.07
     species
    0.07
    orro
    0.07
    acia
    0.07
     variety
    0.07
    apa
    0.07
    Activations Density 0.034%

    No Known Activations