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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 74900
    Prev
    Next
    INDEX
    Explanations

    symbols and characters used in programming or markup language syntax

    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
    odore
    -0.08
    abase
    -0.07
    ASP
    -0.07
    ÙĪراÙĨ
    -0.07
    ĶåĽŀ
    -0.07
    ashi
    -0.07
    furt
    -0.07
    ासन
    -0.07
    PageIndex
    -0.07
    ooth
    -0.07
    POSITIVE LOGITS
    ucz
    0.06
    ÑĢаÑģÑĤа
    0.06
    lamaz
    0.06
    //*
    0.06
     Zw
    0.06
    avage
    0.05
     bacheca
    0.05
    plied
    0.05
     fondo
    0.05
    /topics
    0.05
    Activations Density 0.009%

    No Known Activations