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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5294
    Prev
    Next
    INDEX
    Explanations

    occurrences of a specific character sequence or encoding in text

    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
    //{{
    -0.08
    ogi
    -0.07
    istra
    -0.07
    umber
    -0.07
    osu
    -0.07
    iare
    -0.07
    ози
    -0.07
    agens
    -0.07
    KHR
    -0.07
    DIRECTORY
    -0.07
    POSITIVE LOGITS
    nez
    0.12
    andez
    0.07
    essen
    0.07
    ussen
    0.07
    elly
    0.06
    no
    0.05
     Wallpaper
    0.05
    esson
    0.05
     Mot
    0.05
    weit
    0.05
    Activations Density 0.004%

    No Known Activations