© 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. 94622
    Prev
    Next
    INDEX
    Explanations

    instances of the word "In" and various related phrases and contexts

    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
     маз
    -0.07
     meiden
    -0.06
    asthan
    -0.06
    жно
    -0.06
    fter
    -0.06
    erto
    -0.06
    ison
    -0.06
    appa
    -0.06
    uckle
    -0.06
    anager
    -0.06
    POSITIVE LOGITS
    zin
    0.07
    anzi
    0.07
    _street
    0.07
    IMIT
    0.06
    ruh
    0.06
    aggio
    0.06
    dorf
    0.06
    åı¦ä¸Ģ
    0.06
    bron
    0.06
    -placeholder
    0.06
    Activations Density 0.019%

    No Known Activations