© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 121440
    Prev
    Next
    INDEX
    Explanations

    references to seeking financial advice and disclaimers about financial information

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    oki
    -0.07
    ợ
    -0.06
    ấu
    -0.06
    Å¡ka
    -0.06
    اء
    -0.06
    ãĥ©ãĤ¤ãĥ³
    -0.06
    YA
    -0.06
    Å¡Å¥
    -0.06
    Ñģклад
    -0.06
    yar
    -0.06
    POSITIVE LOGITS
     consult
    0.10
     always
    0.09
    consult
    0.09
     consultation
    0.08
     Consult
    0.08
     consulting
    0.08
    ellas
    0.08
     consulted
    0.08
     ultimately
    0.07
     Always
    0.07
    Activations Density 0.019%

    No Known Activations