© 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. 71005
    Prev
    Next
    INDEX
    Explanations

    mentions of cybersecurity threats and measures

    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
     Murder
    -0.07
    lector
    -0.06
    adora
    -0.06
    Unsafe
    -0.06
    anca
    -0.06
     blood
    -0.06
    urn
    -0.06
    ãĥķãĤ
    -0.06
     Cur
    -0.06
    (Handle
    -0.06
    POSITIVE LOGITS
     attack
    0.09
     attacks
    0.08
     vect
    0.08
     sophistication
    0.07
     Target
    0.07
     cyber
    0.07
     targeting
    0.07
     Attack
    0.07
     Attacks
    0.07
     threat
    0.07
    Activations Density 0.023%

    No Known Activations