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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 89589
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant impacts or effects in health and policy contexts

    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
     неÑİ
    -0.07
    ÄįÃŃ
    -0.07
    ذ
    -0.06
    ISCO
    -0.06
    áj
    -0.06
     chung
    -0.06
    scient
    -0.06
    abela
    -0.06
    CLU
    -0.06
    RIEND
    -0.06
    POSITIVE LOGITS
    oredProcedure
    0.06
    âĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģ
    0.06
    /cop
    0.06
    iro
    0.06
    моÑģ
    0.06
    irus
    0.06
    onte
    0.06
    icker
    0.06
    ®
    0.06
     cul
    0.06
    Activations Density 0.269%

    No Known Activations