© 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. 78503
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional or sensory experiences associated with "feel."

    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
    eteria
    -0.07
    quo
    -0.07
    idth
    -0.07
     же
    -0.07
    们
    -0.07
    éļĽ
    -0.07
    Å©i
    -0.07
    isko
    -0.07
    acters
    -0.07
    olars
    -0.07
    POSITIVE LOGITS
    ings
    0.10
    -good
    0.08
    inspace
    0.08
    illy
    0.07
    ingly
    0.07
    afort
    0.07
    lessly
    0.07
    604
    0.07
    424
    0.07
    ingen
    0.06
    Activations Density 0.005%

    No Known Activations