© 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. 131031
    Prev
    Next
    INDEX
    Explanations

    conditional statements and phrases about user interaction on websites

    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
    initializer
    -0.07
     cloth
    -0.07
    isser
    -0.06
    neys
    -0.06
     Larson
    -0.06
    WARDED
    -0.06
    çĬ¬
    -0.06
    ancellable
    -0.06
    uÅŁ
    -0.06
    assium
    -0.06
    POSITIVE LOGITS
    ano
    0.08
    ustum
    0.07
     doma
    0.07
    atra
    0.06
    راد
    0.06
    ãĥ³ãĥĨãĤ£
    0.06
    .openg
    0.06
    arge
    0.06
    зÑĸ
    0.06
    phins
    0.06
    Activations Density 0.002%

    No Known Activations