© 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. 9-LLAMASCOPE-RES-131K
    11. 95417
    Prev
    Next
    INDEX
    Explanations

    specific phrases or names related to various entities and proper nouns

    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
    Ìģt
    -0.06
    lean
    -0.06
     dve
    -0.06
    ghan
    -0.06
    czy
    -0.06
    å°ĸ
    -0.06
     ãĢ
    -0.06
     gó
    -0.06
     Gow
    -0.06
    ̧
    -0.06
    POSITIVE LOGITS
    ERING
    0.07
    ava
    0.07
    ocrates
    0.07
    ationally
    0.07
    metric
    0.07
    ¢åįķ
    0.07
    .Transactional
    0.06
    eza
    0.06
    ава
    0.06
    odes
    0.06
    Activations Density 0.014%

    No Known Activations