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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 90883
    Prev
    Next
    INDEX
    Explanations

    call-to-action phrases indicating urgency or immediate engagement

    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
    oll
    -0.07
    ayas
    -0.06
    esser
    -0.06
    anner
    -0.06
    ords
    -0.06
    yles
    -0.06
    isha
    -0.06
     Kahn
    -0.06
    okit
    -0.06
    olk
    -0.06
    POSITIVE LOGITS
    inqu
    0.08
    å¾Ħ
    0.08
    รà¸ĵ
    0.07
    butt
    0.07
    /Dk
    0.07
     konkrét
    0.07
    ì¹
    0.07
     Colum
    0.07
    905
    0.06
    ãģĵãĤĵ
    0.06
    Activations Density 0.001%

    No Known Activations