© 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. 107281
    Prev
    Next
    INDEX
    Explanations

    references to the term "Bah" and variations of it, including related entities or geographical mentions

    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
    intel
    -0.07
    urent
    -0.07
    ACLE
    -0.07
    bred
    -0.06
    geries
    -0.06
    ellido
    -0.06
    HIP
    -0.06
    fleet
    -0.06
    acle
    -0.06
    omaly
    -0.06
    POSITIVE LOGITS
    artz
    0.07
    lsen
    0.07
    dbg
    0.06
    ekk
    0.06
    ãĤ·ãĤ¢
    0.06
    TIM
    0.06
    @Web
    0.06
    bk
    0.06
     Crane
    0.06
    illus
    0.06
    Activations Density 0.005%

    No Known Activations