© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126367
    Prev
    Next
    INDEX
    Explanations

    instances of the word "just" in different 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
    oke
    -0.08
    ensburg
    -0.07
    emes
    -0.07
    oze
    -0.07
    ittel
    -0.06
    isset
    -0.06
    ÑĥÑĢн
    -0.06
    ạ
    -0.06
    ertino
    -0.06
    pez
    -0.06
    POSITIVE LOGITS
     few
    0.07
     those
    0.07
    åĩłä¸ª
    0.07
    thag
    0.07
    zens
    0.06
    że
    0.06
    zell
    0.06
    ampions
    0.06
    ZA
    0.06
     Tin
    0.06
    Activations Density 0.001%

    No Known Activations