© 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. 61038
    Prev
    Next
    INDEX
    Explanations

    elements related to inquiries or queries

    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
    ưỡng
    -0.07
    acio
    -0.07
    eker
    -0.07
    425
    -0.07
    ektor
    -0.07
    Ñīина
    -0.07
    едж
    -0.07
    Ñĥп
    -0.07
    .Ptr
    -0.07
    ubic
    -0.06
    POSITIVE LOGITS
    iamond
    0.06
    ÏĥÏĦÏģο
    0.06
     sophisticated
    0.05
    -webpack
    0.05
    utes
    0.05
     bundles
    0.05
    -h
    0.05
    bundles
    0.05
     sophistication
    0.05
     explan
    0.05
    Activations Density 0.000%

    No Known Activations