© 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. 4484
    Prev
    Next
    INDEX
    Explanations

    references to security incidents and their frequency

    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
    xbd
    -0.08
    aldi
    -0.07
     Mill
    -0.07
    getOption
    -0.06
    ritch
    -0.06
    umen
    -0.06
    οÏħÏĥ
    -0.06
     mill
    -0.06
     bud
    -0.06
    _cm
    -0.06
    POSITIVE LOGITS
    utherford
    0.07
    æ¯Ĵ
    0.07
     weekly
    0.06
    ktop
    0.06
    oby
    0.06
    ç¹Ķ
    0.06
    oti
    0.06
     Weekly
    0.06
    irim
    0.06
     attack
    0.06
    Activations Density 0.001%

    No Known Activations