Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. MLP Out
    5. 29-LLAMASCOPE-MLP-131K
    6. 5069
    Prev
    Next
    INDEX
    Explanations

    keywords related to cybersecurity vulnerabilities and 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
     attack
    -0.44
     Attack
    -0.44
     attacks
    -0.41
     attacked
    -0.39
    Attack
    -0.38
     Attacks
    -0.38
    attack
    -0.37
     attacking
    -0.37
     ATTACK
    -0.36
    attacks
    -0.33
    POSITIVE LOGITS
    armed
    0.08
     unarmed
    0.08
     armed
    0.08
     Armed
    0.08
    .GetBytes
    0.08
     gun
    0.08
     guns
    0.08
    ToProps
    0.08
    ÑĤÑİ
    0.08
     Gun
    0.07
    Activations Density 0.129%

    No Known Activations