© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 130749
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional distress and concern

    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
    Advertisements
    -0.06
     argument
    -0.06
     spy
    -0.06
     Passenger
    -0.06
    ByExample
    -0.06
    Arguments
    -0.06
     calendar
    -0.06
    .lin
    -0.05
     malt
    -0.05
    RIPT
    -0.05
    POSITIVE LOGITS
    stay
    0.07
    updates
    0.07
     Updates
    0.07
     evacuation
    0.07
     surreal
    0.07
     evacuated
    0.07
    illac
    0.07
     вÑĥз
    0.07
    _updates
    0.07
     ash
    0.07
    Activations Density 0.009%

    No Known Activations