© 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. 17-LLAMASCOPE-RES-131K
    6. 71743
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions related to language structure

    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
    аниÑĨ
    -0.06
    olle
    -0.06
    onna
    -0.06
    erdem
    -0.06
    unsch
    -0.06
    irs
    -0.06
    aland
    -0.05
    hart
    -0.05
    hold
    -0.05
    _below
    -0.05
    POSITIVE LOGITS
    ovsky
    0.08
    Ø´ÙĪ
    0.07
    ume
    0.07
     Herc
    0.07
    KEN
    0.07
    ENCH
    0.06
    ÙĴس
    0.06
    ocz
    0.06
     wholes
    0.06
    çĤī
    0.06
    Activations Density 0.001%

    No Known Activations