© 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. 129200
    Prev
    Next
    INDEX
    Explanations

    phrases related to security and encryption vulnerabilities

    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
    (#)
    -0.07
    à¹Ħ
    -0.06
    ÙĪØŃ
    -0.06
    autos
    -0.06
    ɵ
    -0.06
    รà¸Ķ
    -0.06
    .Transactional
    -0.06
     Herbert
    -0.06
    -role
    -0.06
     neighb
    -0.06
    POSITIVE LOGITS
     defenses
    0.08
     defeat
    0.08
     techniques
    0.07
     ...,
    0.07
     efficacy
    0.07
    ancock
    0.07
    azzi
    0.06
    icum
    0.06
     weaknesses
    0.06
     defeated
    0.06
    Activations Density 0.017%

    No Known Activations