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

    Neuronpedia

    Jacobian LensNEW
    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. 59330
    Prev
    Next
    INDEX
    Explanations

    instances of the word "already" 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
     nÃło
    -0.07
     ainda
    -0.07
     ancora
    -0.07
    éc
    -0.06
    antan
    -0.06
     aún
    -0.06
    ãģłãģij
    -0.06
    lesc
    -0.06
    çĶ
    -0.06
     Still
    -0.06
    POSITIVE LOGITS
    -existing
    0.10
    t
    0.09
     давно
    0.08
    zeitig
    0.07
    existing
    0.07
     existing
    0.07
    ovnÄĽ
    0.07
    /rss
    0.07
     been
    0.07
    ÑģÑĤÑĮ
    0.07
    Activations Density 0.020%

    No Known Activations