© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 88456
    Prev
    Next
    INDEX
    Explanations

    terms related to examination or close evaluation

    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
    eyh
    -0.08
    cheng
    -0.08
    kola
    -0.08
    o
    -0.07
    enter
    -0.07
    yen
    -0.07
    aign
    -0.07
    cola
    -0.07
    ch
    -0.07
    gui
    -0.07
    POSITIVE LOGITS
    ously
    0.07
    tainment
    0.07
    -minded
    0.07
     minded
    0.07
    naire
    0.06
    ìĦľëĬĶ
    0.06
     BaseService
    0.06
    ìĤ¬íķŃ
    0.06
    andin
    0.06
    reesome
    0.06
    Activations Density 0.002%

    No Known Activations