© 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. 15-LLAMASCOPE-RES-131K
    11. 381
    Prev
    Next
    INDEX
    Explanations

    topics related to home repair and maintenance

    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
    .cloud
    -0.07
    Mapper
    -0.07
    omit
    -0.07
    ucid
    -0.06
    OnUiThread
    -0.06
    anja
    -0.06
     Zimmer
    -0.06
    æIJ¬
    -0.06
    \R
    -0.06
    Reusable
    -0.06
    POSITIVE LOGITS
    ani
    0.06
    ospace
    0.06
    aret
    0.06
    åı°
    0.06
     pocket
    0.06
    753
    0.05
     alc
    0.05
    Âı
    0.05
    _tac
    0.05
    ainment
    0.05
    Activations Density 0.000%

    No Known Activations