© 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. 75020
    Prev
    Next
    INDEX
    Explanations

    references to government initiatives and funding plans

    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
    rien
    -0.08
    stroy
    -0.07
    rů
    -0.07
     èĩªåĬ¨çĶŁæĪIJ
    -0.07
    notated
    -0.06
    abbr
    -0.06
    ober
    -0.06
    Ïģθ
    -0.06
     enim
    -0.06
    longleftrightarrow
    -0.06
    POSITIVE LOGITS
     new
    0.06
    dou
    0.06
    asca
    0.06
    deniz
    0.06
     pilot
    0.06
     tool
    0.06
     formation
    0.06
     Bradley
    0.06
    INDER
    0.06
     soon
    0.06
    Activations Density 0.036%

    No Known Activations