© 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. 39562
    Prev
    Next
    INDEX
    Explanations

    references to meetings, decisions, and collaborative actions

    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
    Âłje
    -0.06
     tô
    -0.06
     tarde
    -0.06
     Köy
    -0.06
     dumping
    -0.06
    stre
    -0.06
     hours
    -0.06
    icult
    -0.06
    vem
    -0.06
    pees
    -0.06
    POSITIVE LOGITS
     next
    0.11
     näch
    0.10
     à¤ħà¤Ĺल
    0.09
    next
    0.08
     session
    0.08
    (next
    0.08
    ,next
    0.08
     upcoming
    0.08
    -next
    0.08
    	next
    0.08
    Activations Density 0.051%

    No Known Activations