© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 85757
    Prev
    Next
    INDEX
    Explanations

    elements related to code structures and functions

    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
    ivic
    -0.07
    assen
    -0.07
    èo
    -0.07
    SSIP
    -0.06
     Flower
    -0.06
    sie
    -0.06
     Cin
    -0.06
     Flag
    -0.06
    _ipv
    -0.06
    Äįin
    -0.06
    POSITIVE LOGITS
     Reaper
    0.07
    åłĤ
    0.06
    é§ħå¾ĴæŃ©
    0.06
     extractor
    0.06
    kas
    0.06
    oldt
    0.06
    ego
    0.06
    kÄĻ
    0.06
    rej
    0.06
    Rub
    0.06
    Activations Density 0.047%

    No Known Activations