© 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. 69935
    Prev
    Next
    INDEX
    Explanations

    references to deadlines and submission processes related to applications or nominations

    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
    hausen
    -0.08
     Lair
    -0.07
    allery
    -0.07
    Ĥ¹
    -0.07
    ki
    -0.07
    ìĬ¹
    -0.07
    stem
    -0.07
    оÑĢаз
    -0.06
    %A
    -0.06
    ienia
    -0.06
    POSITIVE LOGITS
    usra
    0.06
     dated
    0.06
    iglia
    0.06
    oder
    0.05
    ียà¸Ļร
    0.05
     Tie
    0.05
    ynom
    0.05
    aeper
    0.05
    åŃIJãģ¯
    0.05
     tie
    0.05
    Activations Density 0.005%

    No Known Activations