© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71902
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with applications, requirements, and structured information

    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
     Duy
    -0.06
    anko
    -0.06
    arcy
    -0.06
    áÄį
    -0.06
    elite
    -0.05
     Eis
    -0.05
     anymore
    -0.05
     Uns
    -0.05
    quet
    -0.05
     turning
    -0.05
    POSITIVE LOGITS
     carefully
    0.10
     careful
    0.08
     thoroughly
    0.08
     attent
    0.08
    azio
    0.07
     before
    0.07
    before
    0.07
     пÑĢежде
    0.07
     OMIT
    0.07
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ
    0.07
    Activations Density 0.020%

    No Known Activations