© 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. 14468
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating differences between groups or conditions

    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
    oris
    -0.07
     zoekt
    -0.07
    ISE
    -0.07
    angen
    -0.07
    éłĵ
    -0.07
    ayla
    -0.07
    ÌĨ
    -0.07
    CHK
    -0.07
     Sı
    -0.06
    .lab
    -0.06
    POSITIVE LOGITS
     those
    0.13
    those
    0.10
     others
    0.10
     Those
    0.10
    Those
    0.09
     themselves
    0.08
     other
    0.08
     their
    0.07
    éĤ£äºĽ
    0.07
     counterparts
    0.07
    Activations Density 0.007%

    No Known Activations