© 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. 86730
    Prev
    Next
    INDEX
    Explanations

    commands and settings related to configurations and overrides in programming or scripting contexts

    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
    uml
    -0.06
    mel
    -0.06
    ëŀį
    -0.06
     cliff
    -0.06
    /util
    -0.06
    inate
    -0.06
     essentially
    -0.05
     Anch
    -0.05
     spont
    -0.05
    /tos
    -0.05
    POSITIVE LOGITS
    via
    0.10
     via
    0.09
    Via
    0.08
     Via
    0.08
    antium
    0.08
    iswa
    0.07
    _via
    0.07
     пеÑĢемен
    0.07
     sett
    0.07
    PARAM
    0.07
    Activations Density 0.035%

    No Known Activations