© 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 EvalsExportsinterp-engineNEWAPI 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. 31157
    Prev
    Next
    INDEX
    Explanations

    phrases related to organization and management of resources

    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
    912
    -0.06
    367
    -0.06
    licated
    -0.06
    umbed
    -0.05
    #Region
    -0.05
    iform
    -0.05
    bsites
    -0.05
    early
    -0.05
    650
    -0.05
    ä¹ĭä¸Ģ
    -0.05
    POSITIVE LOGITS
     resume
    0.20
     resumed
    0.20
     again
    0.20
     resumes
    0.19
    resume
    0.19
     wieder
    0.17
     Resume
    0.17
    again
    0.17
    Resume
    0.16
     weer
    0.15
    Activations Density 0.084%

    No Known Activations