© 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. 85308
    Prev
    Next
    INDEX
    Explanations

    terms related to regulatory agencies and their classifications

    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
    ucu
    -0.07
    ÄĽj
    -0.06
    mag
    -0.06
    Ä©
    -0.06
    unlikely
    -0.06
    aron
    -0.06
    ा:
    -0.06
     Hlav
    -0.06
    ỹ
    -0.06
    ument
    -0.06
    POSITIVE LOGITS
    ï¼īãģ¯
    0.09
    )ìĿĢ
    0.08
    )ëĬĶ
    0.07
    ô
    0.07
    ")!=
    0.07
    ]
    0.07
    )
    0.07
    ANNOT
    0.07
    attery
    0.07
    "is
    0.07
    Activations Density 0.139%

    No Known Activations