© 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. 5239
    Prev
    Next
    INDEX
    Explanations

    references to mental states and cognitive evaluations during an incident

    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
    assi
    -0.07
    .AutoComplete
    -0.07
     ÏĢε
    -0.07
    èĩ¨
    -0.07
    ebo
    -0.07
    nection
    -0.07
    ipc
    -0.07
    istrovstvÃŃ
    -0.07
    asje
    -0.07
    cie
    -0.07
    POSITIVE LOGITS
    oyal
    0.06
    ách
    0.06
     vom
    0.06
     initially
    0.05
    710
    0.05
    Ram
    0.05
     allegedly
    0.05
     odor
    0.05
    ilter
    0.05
     partitions
    0.05
    Activations Density 0.002%

    No Known Activations