© 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 EvalsExportsinterp-engineNEWAPI 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. 93173
    Prev
    Next
    INDEX
    Explanations

    instances of the word "also" and related phrases indicating additional information or connections

    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
     sice
    -0.07
    èĻ½çĦ¶
    -0.07
    ilib
    -0.07
     Garland
    -0.07
    dae
    -0.07
    /shop
    -0.07
    buz
    -0.06
    ëł´
    -0.06
     erotische
    -0.06
    arov
    -0.06
    POSITIVE LOGITS
     simultaneously
    0.12
     concurrently
    0.10
     ALSO
    0.09
     simultaneous
    0.08
    ä¹Łæĺ¯
    0.08
     doubles
    0.08
     also
    0.07
    åIJĮæĻĤ
    0.07
    åIJĮæŶ
    0.07
     Also
    0.07
    Activations Density 0.048%

    No Known Activations