© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 128155
    Prev
    Next
    INDEX
    Explanations

    references to recovery resources and treatment information

    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
    elia
    -0.07
    ItemAt
    -0.06
     Rivera
    -0.06
    callbacks
    -0.06
    bral
    -0.06
    Enumerable
    -0.06
    aign
    -0.06
    bam
    -0.06
    GetPosition
    -0.06
    avig
    -0.06
    POSITIVE LOGITS
    maz
    0.06
    Ä°T
    0.06
    اÙĨÙĩ
    0.06
    polator
    0.06
    APP
    0.05
    /-
    0.05
    ettings
    0.05
     Nacht
    0.05
     settings
    0.05
    æĸ½
    0.05
    Activations Density 0.000%

    No Known Activations