© 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. 9-LLAMASCOPE-RES-131K
    11. 94372
    Prev
    Next
    INDEX
    Explanations

    references to specific cultural or ethnic identities

    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
    oko
    -0.07
    ,
    -0.07
    :
    -0.06
    orem
    -0.06
    moil
    -0.06
    ufen
    -0.06
    atal
    -0.06
    /
    -0.06
    lop
    -0.06
    stadt
    -0.06
    POSITIVE LOGITS
    ãĥĵãĥ¼
    0.07
    ýš
    0.07
    'gc
    0.07
     serta
    0.07
    ìĥĪ
    0.07
    timeofday
    0.07
    à¹Ģà¸Ĺà¸ŀ
    0.07
    âĢ¦↵↵↵
    0.07
    веÑģÑĤи
    0.06
    곤
    0.06
    Activations Density 0.083%

    No Known Activations