© 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. 17247
    Prev
    Next
    INDEX
    Explanations

    instances of descriptive adjectives or quantifiers

    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
    olini
    -0.07
    ordan
    -0.07
    enso
    -0.07
    <KeyValuePair
    -0.07
    дам
    -0.07
    ologue
    -0.07
    entiful
    -0.06
    lrt
    -0.06
    indrome
    -0.06
     ydk
    -0.06
    POSITIVE LOGITS
     focus
    0.09
     base
    0.08
     history
    0.08
     duty
    0.08
     suite
    0.07
     philosophy
    0.07
     mission
    0.07
    RIA
    0.07
    è
    0.06
     missions
    0.06
    Activations Density 0.018%

    No Known Activations