© 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. 82675
    Prev
    Next
    INDEX
    Explanations

    concepts related to organizational structure and efficiency

    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
    eli
    -0.07
    391
    -0.06
    _UID
    -0.06
    ouse
    -0.06
    عÙģ
    -0.06
     kin
    -0.06
     اÙĨد
    -0.06
    ONO
    -0.06
    ÙĤب
    -0.06
    GNU
    -0.06
    POSITIVE LOGITS
    //{{
    0.07
    ampie
    0.06
    asons
    0.06
    ienne
    0.06
    anders
    0.06
    amma
    0.06
    ocker
    0.06
    formance
    0.06
     extrav
    0.06
    ofilm
    0.06
    Activations Density 0.000%

    No Known Activations