© 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. 104605
    Prev
    Next
    INDEX
    Explanations

    statements related to legal allegations and reports

    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
    buah
    -0.06
    lain
    -0.06
    rollers
    -0.06
    ìĭ¬
    -0.06
    .gwt
    -0.06
    _IW
    -0.06
    nap
    -0.06
    ceeded
    -0.05
    æŃ
    -0.05
     announc
    -0.05
    POSITIVE LOGITS
    orton
    0.07
     dodge
    0.07
    arih
    0.07
    _frontend
    0.06
     ÑĤепеÑĢÑĮ
    0.06
    timeline
    0.06
     revelation
    0.06
    ona
    0.06
     now
    0.06
    jes
    0.06
    Activations Density 0.016%

    No Known Activations