© 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. 74329
    Prev
    Next
    INDEX
    Explanations

    requests or mentions of information relating to products and services

    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
    marshaller
    -0.07
    mast
    -0.07
    ÅĽcie
    -0.07
     setC
    -0.07
    aye
    -0.07
    agrid
    -0.07
     Incontri
    -0.07
    жд
    -0.07
    396
    -0.07
    ombine
    -0.06
    POSITIVE LOGITS
     assistance
    0.06
    ibs
    0.06
    åĩ
    0.06
     help
    0.06
     favors
    0.06
    lice
    0.06
    anim
    0.06
     permission
    0.06
    imar
    0.06
     Whe
    0.06
    Activations Density 0.038%

    No Known Activations