© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126935
    Prev
    Next
    INDEX
    Explanations

    conditional statements involving the word "if" and the past perfect "had"

    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
    olkien
    -0.07
    berman
    -0.07
     Weather
    -0.07
    aza
    -0.07
    icensed
    -0.06
    inou
    -0.06
     Dude
    -0.06
    adla
    -0.06
    ostel
    -0.06
    vla
    -0.06
    POSITIVE LOGITS
    \Helpers
    0.06
     tele
    0.06
    ear
    0.06
    est
    0.06
    eve
    0.06
     Ng
    0.05
    odash
    0.05
    ç·Ĵ
    0.05
    stairs
    0.05
     economics
    0.05
    Activations Density 0.015%

    No Known Activations