© 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. 93528
    Prev
    Next
    INDEX
    Explanations

    terms related to cybersecurity vulnerabilities and their implications

    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
    Interop
    -0.08
    ông
    -0.07
    @js
    -0.07
    ÑĢаÐ
    -0.07
    .accounts
    -0.07
    гал
    -0.07
    .cls
    -0.07
    ÑĪев
    -0.07
    çĿĽ
    -0.07
    .getElements
    -0.07
    POSITIVE LOGITS
    setStatus
    0.06
    amber
    0.06
     Lust
    0.06
    usta
    0.06
     likewise
    0.06
    emi
    0.06
    hive
    0.06
    imilar
    0.05
    usters
    0.05
    init
    0.05
    Activations Density 0.094%

    No Known Activations