© 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. 118196
    Prev
    Next
    INDEX
    Explanations

    timestamps or time-related information

    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
    oft
    -0.07
    itu
    -0.06
    èĻ
    -0.06
    itere
    -0.06
    estre
    -0.06
    GORITH
    -0.06
    kili
    -0.06
    errat
    -0.06
    OKIE
    -0.06
    slow
    -0.06
    POSITIVE LOGITS
    ätt
    0.09
     frau
    0.06
    Bounding
    0.06
    西çľģ
    0.06
    .Syntax
    0.06
    INCLUDE
    0.06
    ØŃÙĤ
    0.06
    ä»
    0.06
     depress
    0.06
    "./
    0.06
    Activations Density 0.002%

    No Known Activations