© 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. 77621
    Prev
    Next
    INDEX
    Explanations

    words associated with discussions or conversations

    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
    @nate
    -0.06
     prophecy
    -0.06
    iren
    -0.06
    orage
    -0.06
    물
    -0.06
    огод
    -0.06
    kin
    -0.06
    ÑĪкÑĥ
    -0.06
    iaux
    -0.06
    irable
    -0.05
    POSITIVE LOGITS
     about
    0.11
    -about
    0.08
    about
    0.08
     tslint
    0.08
    .about
    0.08
     About
    0.07
    itzer
    0.07
    isode
    0.07
     how
    0.06
    ris
    0.06
    Activations Density 0.007%

    No Known Activations