© 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. 74237
    Prev
    Next
    INDEX
    Explanations

    words related to arrival or coming into a place or situation

    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
    ijing
    -0.09
    esters
    -0.08
    estion
    -0.07
    .Sdk
    -0.07
    itori
    -0.07
    offee
    -0.07
     Bret
    -0.07
    iatric
    -0.06
    ï½¥
    -0.06
    oward
    -0.06
    POSITIVE LOGITS
    olate
    0.06
    ival
    0.06
     dose
    0.06
     mutil
    0.06
     doses
    0.06
    vale
    0.06
    forder
    0.06
     dram
    0.06
    ÄįÃŃ
    0.06
     companion
    0.06
    Activations Density 0.010%

    No Known Activations