© 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. 107134
    Prev
    Next
    INDEX
    Explanations

    instructions related to application preparation and presentation

    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
    steen
    -0.08
    modo
    -0.08
    iso
    -0.07
    isos
    -0.07
    upp
    -0.07
    ril
    -0.07
    ICC
    -0.07
    allery
    -0.07
    iec
    -0.07
    iat
    -0.07
    POSITIVE LOGITS
     writer
    0.07
     writing
    0.07
     writers
    0.07
     Writing
    0.07
     Writers
    0.06
     pens
    0.06
     write
    0.06
     writes
    0.06
     notes
    0.06
     Writer
    0.06
    Activations Density 0.011%

    No Known Activations