© 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. 30453
    Prev
    Next
    INDEX
    Explanations

    references to threats or dangerous activities

    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
    heid
    -0.08
    ecast
    -0.08
    hee
    -0.08
    ascular
    -0.08
    ephir
    -0.07
    abei
    -0.07
    gesi
    -0.07
    ñana
    -0.07
     små
    -0.07
    ãģ
    -0.07
    POSITIVE LOGITS
    avers
    0.06
    åħ³
    0.06
    0.05
     Get
    0.05
    _framework
    0.05
    TECTED
    0.05
     Ñħв
    0.05
    ãģªãģıãģª
    0.05
    ÙijÙİ
    0.05
    [src
    0.05
    Activations Density 0.000%

    No Known Activations