© 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. 89716
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the topic of "carrots" and various forms or aspects of them

    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
    arto
    -0.07
    kl
    -0.07
    oteric
    -0.07
    rif
    -0.06
    woff
    -0.06
    kos
    -0.06
    erty
    -0.06
    naire
    -0.06
    evi
    -0.06
    лаг
    -0.06
    POSITIVE LOGITS
    INGTON
    0.08
    ls
    0.08
    asan
    0.08
    agem
    0.08
    pool
    0.08
    ibbean
    0.07
    -Semit
    0.07
    acter
    0.07
    thers
    0.07
    bage
    0.07
    Activations Density 0.054%

    No Known Activations