© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 128338
    Prev
    Next
    INDEX
    Explanations

    links to websites or calls to action for further engagement

    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
    'gc
    -0.06
    yw
    -0.06
    JKLMNOP
    -0.06
    Ñī
    -0.06
     mut
    -0.06
     Yao
    -0.06
     Lav
    -0.06
     thro
    -0.06
     �
    -0.05
     ar
    -0.05
    POSITIVE LOGITS
    adol
    0.07
    ëĭĪìĬ¤
    0.07
    /Foundation
    0.07
    ĥĿ
    0.06
    iniz
    0.06
    stad
    0.06
    eck
    0.06
    à¹Ģà¸Ħล
    0.06
     Tage
    0.06
    resi
    0.06
    Activations Density 0.003%

    No Known Activations