© 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. 15614
    Prev
    Next
    INDEX
    Explanations

    filesystem or directory paths in code

    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
     McGu
    -0.07
    ork
    -0.06
    aps
    -0.06
    obra
    -0.06
    iol
    -0.06
     oby
    -0.06
     doz
    -0.06
    sat
    -0.06
    uong
    -0.06
    eturn
    -0.06
    POSITIVE LOGITS
    /../
    0.10
    ìĪł
    0.07
    ipay
    0.07
     Wenger
    0.07
    Äįel
    0.07
    ázd
    0.07
    	Copyright
    0.07
    IVED
    0.07
    ï¸
    0.07
    ãģĿ
    0.06
    Activations Density 0.004%

    No Known Activations