© 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. 125555
    Prev
    Next
    INDEX
    Explanations

    terms related to vulnerability exploits and denial of service attacks

    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
    iversit
    -0.07
     sop
    -0.07
     Howard
    -0.07
    ukarı
    -0.07
    ropol
    -0.06
    AEA
    -0.06
     Mehr
    -0.06
    adelphia
    -0.06
    .UnitTesting
    -0.06
     mamm
    -0.06
    POSITIVE LOGITS
    VML
    0.07
    ulan
    0.06
     explo
    0.06
    esor
    0.06
    adow
    0.06
    lei
    0.06
    .bid
    0.06
     Cust
    0.06
     gain
    0.06
    ulin
    0.06
    Activations Density 0.014%

    No Known Activations