© 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. 15165
    Prev
    Next
    INDEX
    Explanations

    positive experiences and quality evaluations related to products or performances

    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
     compens
    -0.07
    232
    -0.06
    388
    -0.06
    279
    -0.06
     may
    -0.06
     Lawrence
    -0.06
     swingers
    -0.06
    cdc
    -0.06
    ëĿ¼ëıĦ
    -0.06
    anes
    -0.05
    POSITIVE LOGITS
     saya
    0.08
    evin
    0.07
    ÑĤÑİ
    0.07
     yesterday
    0.07
    COMPARE
    0.07
    æĺ¨
    0.07
    HING
    0.07
    calar
    0.07
     tôi
    0.07
    让æĪij
    0.06
    Activations Density 0.020%

    No Known Activations