© 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. 14868
    Prev
    Next
    INDEX
    Explanations

    keywords related to cybersecurity and malware

    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
    /GPL
    -0.08
     calls
    -0.06
     Abram
    -0.06
     call
    -0.06
    /portfolio
    -0.06
    kid
    -0.06
    660
    -0.06
    ubs
    -0.06
    _TRANS
    -0.05
    ipes
    -0.05
    POSITIVE LOGITS
    _MA
    0.07
    екÑģи
    0.06
    tlement
    0.06
    ãĥ¼ãĥĦ
    0.06
    andest
    0.06
    .getComponent
    0.06
    å¤
    0.06
    \Bundle
    0.06
    idden
    0.06
    ORIZATION
    0.06
    Activations Density 0.000%

    No Known Activations