© 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. 81409
    Prev
    Next
    INDEX
    Explanations

    dialogue or conversational exchanges among characters

    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
    enberg
    -0.08
    /**č↵
    -0.07
    TURN
    -0.07
    èo
    -0.07
    /*č↵
    -0.07
    rank
    -0.07
    ija
    -0.07
    ">ÃĹ</
    -0.07
    олод
    -0.07
    ysa
    -0.07
    POSITIVE LOGITS
     yes
    0.09
    otos
    0.07
     Yes
    0.07
    Yes
    0.06
    yes
    0.06
    rå
    0.06
     YES
    0.06
     ach
    0.06
    chter
    0.06
    menin
    0.06
    Activations Density 0.006%

    No Known Activations