© 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. 92189
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experience and emotional reactions

    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
    .retry
    -0.06
    ipop
    -0.06
    _cuda
    -0.06
    ixin
    -0.06
    essel
    -0.06
    atori
    -0.06
     Pier
    -0.06
    ucky
    -0.06
    Inspectable
    -0.06
    mith
    -0.06
    POSITIVE LOGITS
    felt
    0.07
    ÃŃnÄĽ
    0.07
     thú
    0.07
     surprisingly
    0.07
    ToProps
    0.07
    ROME
    0.07
    .scalablytyped
    0.07
     felt
    0.07
     дейÑģÑĤв
    0.07
     feels
    0.07
    Activations Density 0.028%

    No Known Activations