© 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. 107340
    Prev
    Next
    INDEX
    Explanations

    instances of the partial string "st"

    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
    s
    -0.09
    umann
    -0.07
    389
    -0.07
    pdata
    -0.07
    sar
    -0.07
    riminator
    -0.07
    év
    -0.06
    d
    -0.06
    mpar
    -0.06
    ska
    -0.06
    POSITIVE LOGITS
    reate
    0.07
     st
    0.07
     oppon
    0.06
    rew
    0.06
    OPS
    0.06
     silent
    0.06
    _hop
    0.06
     surve
    0.06
    CELER
    0.06
    ci
    0.06
    Activations Density 0.017%

    No Known Activations