© 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. 22-LLAMASCOPE-RES-131K
    11. 4002
    Prev
    Next
    INDEX
    Explanations

    phrases that describe states or qualities

    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
    究
    -0.07
    arkan
    -0.06
     Castle
    -0.06
    ække
    -0.06
    WithName
    -0.06
    oplast
    -0.06
     gå
    -0.06
    uestion
    -0.06
    ahu
    -0.06
    äll
    -0.06
    POSITIVE LOGITS
     description
    0.20
     describing
    0.19
     descriptions
    0.19
     describe
    0.18
     describes
    0.17
    description
    0.17
     descri
    0.17
     Description
    0.17
     Describe
    0.17
     descriptors
    0.16
    Activations Density 0.030%

    No Known Activations