© 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. 15-LLAMASCOPE-RES-131K
    6. 26924
    Prev
    Next
    INDEX
    Explanations

    terms related to Digital Rights Management (DRM) and copyright issues

    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
    ç°
    -0.07
    425
    -0.06
    IEW
    -0.06
    USD
    -0.06
    dot
    -0.06
    arf
    -0.06
     FX
    -0.06
    Stencil
    -0.06
    .mods
    -0.06
    ovich
    -0.05
    POSITIVE LOGITS
     protection
    0.07
     enf
    0.07
    antic
    0.07
     Alice
    0.07
     circum
    0.06
     Content
    0.06
     protecting
    0.06
     TMPro
    0.06
     ÑĥÑģл
    0.06
    ç´
    0.06
    Activations Density 0.007%

    No Known Activations