© 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 EvalsExportsinterp-engineNEWAPI 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. 116956
    Prev
    Next
    INDEX
    Explanations

    keywords related to societal issues and structures

    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
    ologically
    -0.07
    ically
    -0.07
    ally
    -0.06
     []
    -0.06
    ì§ľ
    -0.06
    ãĤĵãģ¨
    -0.06
    ayıp
    -0.06
    upertino
    -0.06
    ãĢģ“
    -0.06
    ẳn
    -0.06
    POSITIVE LOGITS
    ãĤ¶ãĥ¼
    0.07
    kel
    0.07
    iasi
    0.06
    oin
    0.06
    ãģ¨ãĤĤ
    0.06
     poil
    0.06
    annt
    0.06
    оÑģÑĥд
    0.06
    .|
    0.06
    aldo
    0.06
    Activations Density 0.092%

    No Known Activations