© 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. 2380
    Prev
    Next
    INDEX
    Explanations

    key terms associated with governance and hierarchy

    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
     temptation
    -0.06
     usual
    -0.06
     tempted
    -0.06
     Jer
    -0.06
    tempt
    -0.05
     face
    -0.05
     ret
    -0.05
    _REASON
    -0.05
    ron
    -0.05
     Kore
    -0.05
    POSITIVE LOGITS
    å¿ħé¡»
    0.17
     requirement
    0.16
     required
    0.16
     must
    0.16
    must
    0.15
     Must
    0.15
    Must
    0.15
    required
    0.15
     Required
    0.14
     require
    0.14
    Activations Density 0.006%

    No Known Activations