© 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. 128038
    Prev
    Next
    INDEX
    Explanations

    references to specific methods, principles, or guidelines in academic or technical discourse

    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
    verbosity
    -0.07
     relevant
    -0.07
    ecer
    -0.07
    ÅĻÃŃž
    -0.06
    inant
    -0.06
    vertex
    -0.06
    олиÑĤ
    -0.06
    relevant
    -0.06
    alto
    -0.06
    suma
    -0.06
    POSITIVE LOGITS
    ommen
    0.09
    Ãłn
    0.07
    quez
    0.07
    รà¸ģ
    0.07
    onica
    0.06
    bjerg
    0.06
    ilities
    0.06
     actionPerformed
    0.06
    /V
    0.06
    smarty
    0.06
    Activations Density 0.469%

    No Known Activations