© 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. 15-LLAMASCOPE-RES-131K
    11. 61345
    Prev
    Next
    INDEX
    Explanations

    references to authoritative sources and definitions

    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
     touched
    -0.06
     touch
    -0.06
    f
    -0.06
    ook
    -0.06
    y
    -0.06
     hack
    -0.05
    -0.05
    ide
    -0.05
    iles
    -0.05
    vro
    -0.05
    POSITIVE LOGITS
    /preferences
    0.07
    ãİ
    0.07
    usercontent
    0.07
     vess
    0.07
    tery
    0.07
    .af
    0.07
    áÅĻe
    0.07
     serg
    0.07
    PRS
    0.07
    /calendar
    0.07
    Activations Density 0.000%

    No Known Activations