© 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. 119020
    Prev
    Next
    INDEX
    Explanations

    phrases that describe processes related to development and organization

    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
    bes
    -0.07
    ãĥ¼ãĥĬ
    -0.07
    ourg
    -0.06
    akov
    -0.06
     alike
    -0.06
    yne
    -0.06
     Uph
    -0.06
    itest
    -0.06
    oup
    -0.06
    å¥
    -0.06
    POSITIVE LOGITS
     pie
    0.07
    ilon
    0.07
     gradually
    0.07
    Truthy
    0.06
    SURE
    0.06
     MERCHANTABILITY
    0.06
    otten
    0.06
    รม
    0.06
    ype
    0.06
    romium
    0.06
    Activations Density 0.011%

    No Known Activations