© 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. 60240
    Prev
    Next
    INDEX
    Explanations

    code-related terms and operations involving file paths and directories

    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
     Hopkins
    -0.06
    iership
    -0.06
     ret
    -0.06
    anship
    -0.06
    ICS
    -0.06
     Brewery
    -0.05
    _pag
    -0.05
    YY
    -0.05
     free
    -0.05
     id
    -0.05
    POSITIVE LOGITS
    akens
    0.07
    USR
    0.07
    ecom
    0.07
    ÙĥÙĪر
    0.07
    agna
    0.07
    atk
    0.07
    ÏĦÏİ
    0.06
     Clem
    0.06
    ÑĢави
    0.06
    пÑĢиклад
    0.06
    Activations Density 0.017%

    No Known Activations