© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106792
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and structure

    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
    ungle
    -0.07
    ãĤ¦ãĥĪ
    -0.07
     Lah
    -0.06
    amer
    -0.06
    ษ
    -0.06
     Fam
    -0.06
     viên
    -0.06
    è¬
    -0.05
    _DEPEND
    -0.05
    vi
    -0.05
    POSITIVE LOGITS
    chine
    0.07
    oru
    0.07
    ardown
    0.07
    kün
    0.07
     misc
    0.07
    thur
    0.07
    POCH
    0.06
    izz
    0.06
    ichick
    0.06
    ñana
    0.06
    Activations Density 0.001%

    No Known Activations