© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90158
    Prev
    Next
    INDEX
    Explanations

    programming class and method definitions

    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
    il
    -0.06
    ut
    -0.06
     Yani
    -0.06
    anni
    -0.06
    away
    -0.06
    lander
    -0.06
    GLOBALS
    -0.06
     fur
    -0.06
    alice
    -0.06
    ا
    -0.05
    POSITIVE LOGITS
    ึà¸ģ
    0.07
    ltra
    0.07
    567
    0.07
    456
    0.06
    _RST
    0.06
    ега
    0.06
    stal
    0.06
    edik
    0.06
    CCR
    0.06
    alsa
    0.06
    Activations Density 0.000%

    No Known Activations