© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 61528
    Prev
    Next
    INDEX
    Explanations

    lists and frequently occurring articles or prepositions

    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
    olumn
    -0.07
    acha
    -0.06
     Appalach
    -0.06
    emouth
    -0.06
    icos
    -0.06
    911
    -0.06
    verty
    -0.06
    arton
    -0.06
    ër
    -0.06
    oter
    -0.05
    POSITIVE LOGITS
    ysz
    0.07
    ((&
    0.07
    WARDED
    0.07
    _FATAL
    0.07
    dsl
    0.06
    æĻ´
    0.06
    .localized
    0.06
    igma
    0.06
    AREST
    0.06
    inya
    0.06
    Activations Density 0.001%

    No Known Activations