© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 60235
    Prev
    Next
    INDEX
    Explanations

    references to physical contact or the sense of touch

    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
    MBER
    -0.07
    mak
    -0.06
    .rl
    -0.06
    Å¡ÃŃ
    -0.06
    ivant
    -0.06
     졸
    -0.06
     GOODMAN
    -0.06
    chter
    -0.06
    otten
    -0.06
    issen
    -0.06
    POSITIVE LOGITS
     Touch
    0.10
     touch
    0.09
    -touch
    0.09
     touched
    0.09
    touch
    0.09
    Touch
    0.09
     touching
    0.09
    (touch
    0.08
     TOUCH
    0.08
    触
    0.08
    Activations Density 0.016%

    No Known Activations