© 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. 60111
    Prev
    Next
    INDEX
    Explanations

    phrases relating to comments or feedback left by readers

    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
    owa
    -0.07
    asar
    -0.07
    rego
    -0.07
    oa
    -0.07
    ncy
    -0.06
    zburg
    -0.06
    bye
    -0.06
    øj
    -0.06
     face
    -0.06
    hei
    -0.06
    POSITIVE LOGITS
     Perf
    0.08
    иÑĩа
    0.07
    equip
    0.07
     Tut
    0.07
    ůst
    0.07
    alent
    0.06
     Ordering
    0.06
     Rox
    0.06
     Orc
    0.06
     perf
    0.06
    Activations Density 0.002%

    No Known Activations