© 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. 40439
    Prev
    Next
    INDEX
    Explanations

    names and mentions of users or individuals related to discussions or topics

    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
    jedn
    -0.09
    ekil
    -0.09
     jedn
    -0.08
    اضر
    -0.08
    ãģĶ
    -0.08
    Longrightarrow
    -0.08
    (çģ«
    -0.08
     Antar
    -0.08
    aleb
    -0.08
    ondo
    -0.08
    POSITIVE LOGITS
     Kash
    0.07
     who
    0.06
    ·
    0.05
     whenever
    0.05
    icle
    0.05
     borderline
    0.05
     Maid
    0.05
     ""
    0.05
    ä¹İ
    0.05
     ''
    0.05
    Activations Density 0.007%

    No Known Activations