© 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. 41665
    Prev
    Next
    INDEX
    Explanations

    expressions emphasizing fairness or balance

    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
    é¨İ
    -0.07
    stras
    -0.07
     ("-
    -0.07
    ืà¹ī
    -0.07
    NewLabel
    -0.06
     antic
    -0.06
    ycz
    -0.06
    zan
    -0.06
    eres
    -0.06
     everybody
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĤ°ãĥ«
    0.06
    peria
    0.06
    F
    0.06
    egov
    0.06
     Cummings
    0.06
    obao
    0.05
    ãĤ¤ãĤº
    0.05
    CF
    0.05
    Util
    0.05
    abbo
    0.05
    Activations Density 0.000%

    No Known Activations