© 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. 27514
    Prev
    Next
    INDEX
    Explanations

    phrases indicating authority or inquiry

    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
    icht
    -0.07
    alo
    -0.06
    037
    -0.06
    enga
    -0.06
    912
    -0.06
    iegel
    -0.06
    610
    -0.06
     tro
    -0.06
     Loren
    -0.06
    707
    -0.06
    POSITIVE LOGITS
    FOUND
    0.08
    eneg
    0.07
    FOUNDATION
    0.07
    ijke
    0.07
    Unnamed
    0.07
    çµ
    0.07
    PIC
    0.07
    .gb
    0.07
    Defense
    0.07
    iyim
    0.07
    Activations Density 0.001%

    No Known Activations