© 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. 17-LLAMASCOPE-RES-131K
    6. 82554
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to diversity in physical characteristics or representations

    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
    çĽĸ
    -0.07
    ãģŁãĤī
    -0.07
     yat
    -0.07
     kì
    -0.07
    ãĥĥãĥĦ
    -0.07
    vault
    -0.07
    æĪ²
    -0.07
     öyle
    -0.07
    à¥įदर
    -0.07
     Guard
    -0.06
    POSITIVE LOGITS
    ofs
    0.06
    plier
    0.06
    adel
    0.06
    uling
    0.05
     .↵
    0.05
    CTest
    0.05
    eteor
    0.05
     flex
    0.05
     Shore
    0.05
    åħĭæĸ¯
    0.05
    Activations Density 0.000%

    No Known Activations