© 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. 87269
    Prev
    Next
    INDEX
    Explanations

    phrases related to ethical and responsible practices, particularly in waste disposal and animal farming

    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
     readily
    -0.08
    AZY
    -0.06
     Simpl
    -0.06
    à¹Īาย
    -0.06
     Mobil
    -0.06
    asics
    -0.06
     waived
    -0.06
     instantly
    -0.06
     immedi
    -0.06
     simplify
    -0.06
    POSITIVE LOGITS
     safe
    0.12
    safe
    0.09
    -safe
    0.09
     safely
    0.09
     proper
    0.09
    proper
    0.09
    Safe
    0.09
     Safe
    0.09
     eth
    0.09
     respectful
    0.08
    Activations Density 0.125%

    No Known Activations