© 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. 128766
    Prev
    Next
    INDEX
    Explanations

    phrases related to compensating for deficiencies or losses

    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
    ##_
    -0.07
    undo
    -0.07
    .isOpen
    -0.07
     doch
    -0.07
     Ø°
    -0.07
    .tk
    -0.07
    ToDevice
    -0.07
    iams
    -0.06
    StateMachine
    -0.06
    ->{_
    -0.06
    POSITIVE LOGITS
     lost
    0.11
    Lost
    0.09
     Lost
    0.09
     missing
    0.08
    lost
    0.08
     lack
    0.07
     missed
    0.07
    _lost
    0.07
     previous
    0.07
     past
    0.07
    Activations Density 0.007%

    No Known Activations