© 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. 56405
    Prev
    Next
    INDEX
    Explanations

    instances of strong criticism or negative sentiments regarding authority figures and processes

    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
    Mari
    -0.07
    ippi
    -0.07
     âĹĦ
    -0.07
    itler
    -0.07
    ï¸
    -0.07
    PIX
    -0.06
    ços
    -0.06
    -widgets
    -0.06
     handleError
    -0.06
    InnerText
    -0.06
    POSITIVE LOGITS
     questions
    0.13
    probe
    0.11
     probing
    0.11
     interviewer
    0.10
     questioning
    0.10
     probe
    0.10
     interview
    0.10
     Interview
    0.10
     grill
    0.10
     probes
    0.10
    Activations Density 0.090%

    No Known Activations