© 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. 105723
    Prev
    Next
    INDEX
    Explanations

    phrases indicating speech or quotations

    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
     spur
    -0.06
     nackte
    -0.06
    åŃĿ
    -0.06
     Victim
    -0.06
     bas
    -0.06
     repl
    -0.05
     gar
    -0.05
    ãĥĨãĥ«
    -0.05
    reuse
    -0.05
    .Actions
    -0.05
    POSITIVE LOGITS
    istar
    0.08
    ól
    0.07
    afen
    0.07
    rena
    0.07
    ä¹ĭä¸Ģ
    0.07
    istol
    0.07
    -Ñħ
    0.06
    dech
    0.06
    ramework
    0.06
    .unsplash
    0.06
    Activations Density 0.012%

    No Known Activations