© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 181
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reluctance or avoidance

    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
    acman
    -0.08
    osci
    -0.08
    ÑĩиÑģ
    -0.08
    ertino
    -0.07
    ãģĿãģĹãģ¦
    -0.07
     yiy
    -0.07
    รà¸ĵ
    -0.07
    importe
    -0.07
    еÑĨ
    -0.07
     amen
    -0.07
    POSITIVE LOGITS
    isode
    0.06
     âĢIJ
    0.05
    548
    0.05
    282
    0.05
    ourt
    0.05
    Callbacks
    0.05
    229
    0.05
     jurisdiction
    0.05
     Pik
    0.05
     repo
    0.05
    Activations Density 0.045%

    No Known Activations