© 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. 70411
    Prev
    Next
    INDEX
    Explanations

    references to objects in pristine or well-preserved condition

    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
     already
    -0.07
     after
    -0.06
    estone
    -0.06
    already
    -0.06
    ,
    -0.06
     Already
    -0.06
     grown
    -0.06
    after
    -0.06
    pac
    -0.06
    же
    -0.06
    POSITIVE LOGITS
     fresh
    0.16
     fres
    0.15
     Fresh
    0.14
    fresh
    0.14
     Ñģвеж
    0.14
    Fresh
    0.14
     freshness
    0.13
     freshly
    0.12
     younger
    0.11
     virgin
    0.10
    Activations Density 0.060%

    No Known Activations