© 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. 82253
    Prev
    Next
    INDEX
    Explanations

    references to conversations or interactions between characters

    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
    лÑĸд
    -0.08
    inea
    -0.07
    enses
    -0.07
    ÑĮÑı
    -0.07
    çĶ
    -0.07
    Recorder
    -0.06
    inee
    -0.06
     Yani
    -0.06
    eyen
    -0.06
     concurrency
    -0.06
    POSITIVE LOGITS
     callers
    0.07
    ozy
    0.06
    icast
    0.06
    ziel
    0.06
    pton
    0.06
    _python
    0.06
    ëĤ
    0.06
     civilian
    0.06
     seins
    0.06
    onym
    0.06
    Activations Density 0.001%

    No Known Activations