© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119564
    Prev
    Next
    INDEX
    Explanations

    actions related to deception or manipulation in medical contexts

    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
    º
    -0.08
    anzi
    -0.07
    _MAJOR
    -0.07
    Äł
    -0.07
    allis
    -0.07
     pedest
    -0.07
    .scalablytyped
    -0.07
     instincts
    -0.07
     оÑĤли
    -0.07
    amble
    -0.06
    POSITIVE LOGITS
     multiple
    0.07
    encers
    0.07
     themselves
    0.07
     just
    0.06
     Strat
    0.06
     simply
    0.06
     often
    0.06
     or
    0.06
     strategically
    0.06
     cheap
    0.06
    Activations Density 0.043%

    No Known Activations