© 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. 15-LLAMASCOPE-RES-131K
    11. 175
    Prev
    Next
    INDEX
    Explanations

    occurrences of coded or technical terms related to programming or data structures

    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
    kate
    -0.08
    fak
    -0.07
    arcer
    -0.07
    tatus
    -0.07
    activex
    -0.06
    inx
    -0.06
     Ansi
    -0.06
    yk
    -0.06
    afia
    -0.06
     pyl
    -0.06
    POSITIVE LOGITS
     input
    0.07
     solic
    0.06
     Cre
    0.06
     quint
    0.06
    idal
    0.06
    NullException
    0.06
     inputs
    0.06
     Tin
    0.06
     Liberty
    0.06
     incident
    0.05
    Activations Density 0.000%

    No Known Activations