© 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. 78541
    Prev
    Next
    INDEX
    Explanations

    terms related to consequences and penalties for wrongdoings

    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
    áºł
    -0.07
    SCO
    -0.07
    ucha
    -0.07
     nav
    -0.06
     somehow
    -0.06
    igham
    -0.06
    otor
    -0.06
    kili
    -0.06
    ONGO
    -0.06
    ighbors
    -0.06
    POSITIVE LOGITS
     permanently
    0.09
    δη
    0.08
     suspension
    0.07
     ban
    0.07
     permanent
    0.07
     temporarily
    0.07
    roker
    0.07
     perman
    0.07
     loss
    0.06
     Bans
    0.06
    Activations Density 0.013%

    No Known Activations