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

    Neuronpedia

    Jacobian LensNEW
    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. 77200
    Prev
    Next
    INDEX
    Explanations

    mentions of creative commons licenses

    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
    enga
    -0.06
    arp
    -0.06
    |wx
    -0.06
    tatus
    -0.06
    ille
    -0.06
    iens
    -0.06
    inch
    -0.06
    iana
    -0.06
    edList
    -0.06
    arnation
    -0.06
    POSITIVE LOGITS
    jer
    0.09
     -*-č↵
    0.07
     licensed
    0.07
     license
    0.07
    вод
    0.07
    ãĤ±ãĥ¼ãĤ¹
    0.07
    itest
    0.07
    /licenses
    0.07
    creativecommons
    0.07
    license
    0.06
    Activations Density 0.001%

    No Known Activations