© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78918
    Prev
    Next
    INDEX
    Explanations

    syntax and structure related to coding, particularly in Objective-C

    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
    athi
    -0.06
    arend
    -0.06
    821
    -0.06
     quake
    -0.06
    ugen
    -0.06
    sic
    -0.06
    (
    -0.06
    iffin
    -0.06
    tres
    -0.06
    endale
    -0.06
    POSITIVE LOGITS
       
    0.07
    istrovstvÃŃ
    0.07
    باد
    0.06
    baÅŁ
    0.06
    ĥn
    0.06
    оÑĩки
    0.06
     bidi
    0.06
    /+
    0.06
    izik
    0.06
    ä¸ļ
    0.06
    Activations Density 0.004%

    No Known Activations