© 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. 15-LLAMASCOPE-RES-131K
    11. 87027
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or requests for assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Phrases indicating uncertainty or difficulty in understanding technical problems, often followed by attempts to describe the issue or solution they're seeking.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    enville
    -0.07
    -fw
    -0.07
    alten
    -0.06
    aset
    -0.06
    {}{↵
    -0.06
    arrass
    -0.06
    asc
    -0.06
    çĽĸ
    -0.06
    shal
    -0.06
    олж
    -0.06
    POSITIVE LOGITS
    ende
    0.06
     Uns
    0.06
    623
    0.06
     맡
    0.06
    ãģ£
    0.06
    ickey
    0.06
    otec
    0.05
     uns
    0.05
     sug
    0.05
    èı
    0.05
    Activations Density 0.010%

    No Known Activations