© 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. 86959
    Prev
    Next
    INDEX
    Explanations

    technical terms and methods related to programming and data serialization

    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
    egin
    -0.07
    tracts
    -0.06
    illac
    -0.06
    ños
    -0.06
    ãĥ¼ãĥį
    -0.06
    Elf
    -0.06
    rending
    -0.06
     bless
    -0.06
    ogie
    -0.06
    αÏĥ
    -0.06
    POSITIVE LOGITS
     Fur
    0.07
    éĻ½
    0.06
     ap
    0.06
     doz
    0.06
     IDirect
    0.06
    _suite
    0.06
    åįĪ
    0.06
    Ãłng
    0.06
     abduction
    0.06
     Ùħرک
    0.06
    Activations Density 0.002%

    No Known Activations