© 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. 72018
    Prev
    Next
    INDEX
    Explanations

    specific words related to permissions and restrictions

    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
    ;element
    -0.08
    -enable
    -0.07
    942
    -0.07
    uga
    -0.07
    akis
    -0.07
    ides
    -0.07
    dea
    -0.07
    ogui
    -0.07
    -tooltip
    -0.07
    _ASCII
    -0.07
    POSITIVE LOGITS
     to
    0.07
     anymore
    0.06
    تر
    0.06
    èĥ¡
    0.06
     Welch
    0.06
    ly
    0.06
    listed
    0.06
     everywhere
    0.06
    igram
    0.06
     anywhere
    0.05
    Activations Density 0.009%

    No Known Activations