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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56312
    Prev
    Next
    INDEX
    Explanations

    references to online gambling and casino-related terms

    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
     Peel
    -0.06
     st
    -0.06
     kr
    -0.06
    dom
    -0.05
    uling
    -0.05
    ady
    -0.05
    omic
    -0.05
     dik
    -0.05
    uble
    -0.05
    JI
    -0.05
    POSITIVE LOGITS
    ettel
    0.10
    illis
    0.08
    utton
    0.08
     Yön
    0.07
    cplusplus
    0.07
     اÙĦرسÙħÙĬ
    0.07
    ainen
    0.07
    .strict
    0.07
    otte
    0.07
    bz
    0.07
    Activations Density 0.010%

    No Known Activations