© 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. 15427
    Prev
    Next
    INDEX
    Explanations

    specific terms related to awards and achievements

    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
    anga
    -0.09
    errer
    -0.09
     GOODMAN
    -0.07
     ÑģоÑħ
    -0.07
    utherford
    -0.07
     à¤®à¤ľ
    -0.07
    anguard
    -0.07
    ZO
    -0.07
    еÑĢин
    -0.07
    GLOBALS
    -0.07
    POSITIVE LOGITS
     Speech
    0.07
     Bras
    0.07
     model
    0.07
     speech
    0.07
    peech
    0.07
     modelling
    0.06
     diet
    0.06
     Miss
    0.06
     Essay
    0.06
     modeling
    0.06
    Activations Density 0.001%

    No Known Activations