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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87266
    Prev
    Next
    INDEX
    Explanations

    references to network security vulnerabilities and attacks involving malformed packets

    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
    okies
    -0.07
     redundant
    -0.07
    amo
    -0.07
    iversit
    -0.06
    lettes
    -0.06
     Rolls
    -0.06
    247
    -0.06
    zin
    -0.06
    oky
    -0.06
    allet
    -0.06
    POSITIVE LOGITS
     malformed
    0.08
     crafted
    0.07
    craft
    0.07
    crafted
    0.07
     Crafting
    0.06
     craft
    0.06
    esium
    0.06
     Rud
    0.06
     ìķħ
    0.06
    arness
    0.06
    Activations Density 0.012%

    No Known Activations