© 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. 117857
    Prev
    Next
    INDEX
    Explanations

    expressions related to positive outcomes or accomplishments

    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
    ymi
    -0.07
     continu
    -0.07
    ansi
    -0.07
    丹
    -0.07
    stead
    -0.07
    enk
    -0.07
     ash
    -0.07
    ilar
    -0.06
    hoe
    -0.06
     Ãĸn
    -0.06
    POSITIVE LOGITS
     something
    0.09
    something
    0.08
    Something
    0.08
     Something
    0.08
    aret
    0.07
    omething
    0.07
    ecut
    0.06
    sko
    0.06
    ÃĹ
    0.06
    insk
    0.05
    Activations Density 0.042%

    No Known Activations