© 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. 4312
    Prev
    Next
    INDEX
    Explanations

    the preposition "to."

    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
    isos
    -0.06
    arp
    -0.06
    idge
    -0.06
    ÃŃm
    -0.06
     fortn
    -0.05
    email
    -0.05
    emand
    -0.05
    isol
    -0.05
    DOI
    -0.05
    ÑĻ
    -0.05
    POSITIVE LOGITS
     Fell
    0.08
    URY
    0.07
     Bounty
    0.07
    byn
    0.06
    .Atomic
    0.06
     ê°¤
    0.06
    ERO
    0.06
    δÏĮν
    0.06
     lez
    0.06
    ButtonItem
    0.06
    Activations Density 0.000%

    No Known Activations