© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 85087
    Prev
    Next
    INDEX
    Explanations

    mentions of cybersecurity incidents and related information

    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
    åłĤ
    -0.07
     surrogate
    -0.07
    aries
    -0.07
    avir
    -0.06
     Year
    -0.06
    fe
    -0.06
     irr
    -0.06
    irl
    -0.06
    aws
    -0.06
    (#)
    -0.06
    POSITIVE LOGITS
    Affected
    0.08
     security
    0.07
    ģm
    0.07
    lero
    0.07
    rowsable
    0.07
    croft
    0.07
    jÃŃ
    0.07
     patch
    0.07
     Security
    0.07
    yk
    0.07
    Activations Density 0.017%

    No Known Activations