© 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. 3593
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and constructs related to research and experimental setups

    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
    oui
    -0.07
     sweep
    -0.07
     Dont
    -0.06
    iris
    -0.06
    ois
    -0.06
    orta
    -0.06
    erto
    -0.06
     että
    -0.06
    eger
    -0.06
    494
    -0.06
    POSITIVE LOGITS
    ascus
    0.07
    atile
    0.07
    arness
    0.06
    anism
    0.06
    ãĥĸãĥª
    0.06
    침
    0.06
    588
    0.06
    -Free
    0.06
     thì
    0.06
    ãĥ
    0.06
    Activations Density 0.051%

    No Known Activations