© 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. 17-LLAMASCOPE-RES-131K
    11. 75963
    Prev
    Next
    INDEX
    Explanations

    questions and inquiry phrases

    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
    umpt
    -0.08
    atte
    -0.07
    usercontent
    -0.06
    esco
    -0.06
    ESCO
    -0.06
     Holt
    -0.06
    inces
    -0.06
    èĶµ
    -0.06
    lok
    -0.06
    mania
    -0.06
    POSITIVE LOGITS
    )did
    0.07
    How
    0.07
     how
    0.07
    Ĥ¨
    0.07
    ëĤĺìļĶ
    0.06
    onn
    0.06
     How
    0.06
    ÄĽle
    0.06
     Does
    0.06
    315
    0.06
    Activations Density 0.011%

    No Known Activations