Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43494
    Prev
    Next
    INDEX
    Explanations

    specific names or references to locations or significant entities

    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
    aye
    -0.08
    æĺĵ
    -0.07
    ISA
    -0.07
    éºĹ
    -0.06
    meye
    -0.06
    å±ħ
    -0.06
     Viv
    -0.06
    SSIP
    -0.06
    Ù¹
    -0.06
    رÙĬر
    -0.06
    POSITIVE LOGITS
    esco
    0.14
    uces
    0.09
    ones
    0.09
    es
    0.09
    esch
    0.08
    ios
    0.08
    cs
    0.08
    ches
    0.08
    isco
    0.08
    de
    0.08
    Activations Density 0.002%

    No Known Activations