© 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. 81783
    Prev
    Next
    INDEX
    Explanations

    references to cyber threats and hacking 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
    icao
    -0.07
    immel
    -0.07
     appeal
    -0.07
    apı
    -0.06
    anca
    -0.06
    bjerg
    -0.06
     Appeal
    -0.06
    atan
    -0.06
    ÄŁan
    -0.06
    jie
    -0.06
    POSITIVE LOGITS
    -target
    0.08
     Target
    0.08
     targeting
    0.08
     TARGET
    0.07
    /target
    0.07
    è
    0.06
    _Target
    0.06
     Actors
    0.06
     Variant
    0.06
    rowsable
    0.06
    Activations Density 0.016%

    No Known Activations