© 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 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. 17-LLAMASCOPE-RES-131K
    11. 3695
    Prev
    Next
    INDEX
    Explanations

    themes related to adaptation and change

    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
    hung
    -0.08
    utin
    -0.07
    ر
    -0.07
    anke
    -0.07
    467
    -0.07
    lÃŃÄį
    -0.07
    hti
    -0.07
    ipzig
    -0.07
    arp
    -0.07
    zeug
    -0.07
    POSITIVE LOGITS
    ively
    0.13
    ability
    0.08
     Gale
    0.07
    ria
    0.07
    atic
    0.07
    ors
    0.06
    ague
    0.06
    ative
    0.06
     dần
    0.06
    iveness
    0.06
    Activations Density 0.012%

    No Known Activations