© 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. 92976
    Prev
    Next
    INDEX
    Explanations

    instances of authority or commands

    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
    łģ
    -0.07
    물
    -0.07
    alyze
    -0.07
    ended
    -0.07
     yanı
    -0.07
    IMA
    -0.07
    _MINUS
    -0.06
    chen
    -0.06
    idding
    -0.06
    kap
    -0.06
    POSITIVE LOGITS
     because
    0.11
    because
    0.08
     reasons
    0.08
     reasoning
    0.07
     reason
    0.07
     instead
    0.07
     Because
    0.07
    Because
    0.07
    çIJĨçĶ±
    0.07
     porque
    0.07
    Activations Density 0.029%

    No Known Activations