© 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 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. 59377
    Prev
    Next
    INDEX
    Explanations

    phrases related to interactions and inquiries

    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
    fur
    -0.06
    heimer
    -0.06
    tons
    -0.06
     повеÑĢ
    -0.06
    kode
    -0.05
    engo
    -0.05
    locker
    -0.05
    ASCADE
    -0.05
     INLINE
    -0.05
    wargs
    -0.05
    POSITIVE LOGITS
     initiative
    0.12
     Initiative
    0.10
     proactive
    0.10
     actively
    0.10
    actively
    0.09
    init
    0.09
     Init
    0.08
     initiate
    0.08
     init
    0.08
     initiation
    0.08
    Activations Density 0.050%

    No Known Activations