© 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. 28667
    Prev
    Next
    INDEX
    Explanations

    mentions of alumni or connections between classmates

    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
     phẩm
    -0.07
    ival
    -0.07
    ẩu
    -0.07
     Huck
    -0.07
    heimer
    -0.06
    رÙĪب
    -0.06
     Crack
    -0.06
    óa
    -0.06
    redential
    -0.06
    inh
    -0.06
    POSITIVE LOGITS
    anka
    0.07
     reunion
    0.06
    NI
    0.06
    .com
    0.06
     fate
    0.06
     gag
    0.06
     reun
    0.06
     meaning
    0.06
    kw
    0.05
     online
    0.05
    Activations Density 0.000%

    No Known Activations