© 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. 15-LLAMASCOPE-RES-131K
    11. 86604
    Prev
    Next
    INDEX
    Explanations

    instances of negotiation and dialogue

    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
    ĥ
    -0.07
    ñana
    -0.07
    ายà¹ĥà¸Ļ
    -0.07
    ificados
    -0.07
    ountry
    -0.07
    akit
    -0.06
    Äįka
    -0.06
    pei
    -0.06
    /feed
    -0.06
    eyh
    -0.06
    POSITIVE LOGITS
    ilen
    0.07
    ings
    0.06
    akh
    0.06
     with
    0.06
     between
    0.06
    227
    0.06
     Mish
    0.06
     Paulo
    0.06
    ξι
    0.06
    icky
    0.06
    Activations Density 0.005%

    No Known Activations