© 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. 14790
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lost."

    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
    istas
    -0.07
    agedList
    -0.07
    onth
    -0.06
    emble
    -0.06
    ĵį
    -0.06
     norm
    -0.06
    ilian
    -0.06
    ista
    -0.06
    asto
    -0.06
    hall
    -0.06
    POSITIVE LOGITS
     lost
    0.08
     forever
    0.08
     sight
    0.08
    Lost
    0.07
     Lost
    0.07
     Forever
    0.07
    ahl
    0.07
     perder
    0.07
     mát
    0.07
    lost
    0.06
    Activations Density 0.005%

    No Known Activations