© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103329
    Prev
    Next
    INDEX
    Explanations

    mentions of various related entities or categories regarding participants or items involved in a system

    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
    ilip
    -0.07
    flen
    -0.07
     treff
    -0.07
     discrepan
    -0.07
    .gz
    -0.07
     arac
    -0.07
    .blog
    -0.07
    antino
    -0.07
    ominator
    -0.06
    _usec
    -0.06
    POSITIVE LOGITS
    ë§Ŀ
    0.06
    æĭħå½ĵ
    0.06
     Category
    0.06
    eken
    0.06
    ody
    0.06
    æ¶ī
    0.06
     Tier
    0.05
    urt
    0.05
    deaux
    0.05
    erval
    0.05
    Activations Density 0.032%

    No Known Activations