© 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. 93961
    Prev
    Next
    INDEX
    Explanations

    instances of the word "received"

    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
    æ²¢
    -0.06
    èŃľ
    -0.06
    erb
    -0.06
    IPH
    -0.06
    ffa
    -0.06
    eniz
    -0.06
     Larger
    -0.06
    .gdx
    -0.06
    ittel
    -0.06
    iterals
    -0.06
    POSITIVE LOGITS
    soever
    0.06
    pus
    0.06
    [--
    0.06
    piration
    0.06
    alers
    0.06
    leep
    0.06
    inou
    0.06
    oline
    0.06
    åŃĹ
    0.06
    ItemSelected
    0.06
    Activations Density 0.000%

    No Known Activations