© 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 EvalsExportsinterp-engineNEWAPI 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. 117966
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration or anger

    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
     gá»ijc
    -0.07
     Panic
    -0.07
    Weak
    -0.06
    adjusted
    -0.06
    eken
    -0.06
     pornos
    -0.06
    èĭ¦
    -0.06
    .intro
    -0.06
    Adjusted
    -0.06
     Metro
    -0.06
    POSITIVE LOGITS
     vent
    0.12
     rage
    0.11
     temper
    0.11
     anger
    0.10
    æĢĴ
    0.10
     rant
    0.09
     angry
    0.09
     fury
    0.09
     Rage
    0.09
     tantr
    0.09
    Activations Density 0.085%

    No Known Activations