© 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. 104466
    Prev
    Next
    INDEX
    Explanations

    terms related to the review and accuracy of documents or data

    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
    kel
    -0.08
    çľ
    -0.07
    å·»
    -0.06
    mrt
    -0.06
    .poly
    -0.06
     collaps
    -0.06
    ymm
    -0.06
    -org
    -0.06
     Insecta
    -0.06
    pii
    -0.05
    POSITIVE LOGITS
     proposed
    0.08
     submitted
    0.08
    adors
    0.08
    submitted
    0.07
    lectric
    0.07
    aghetti
    0.06
    rient
    0.06
    åħ¼
    0.06
     appropri
    0.06
    iani
    0.06
    Activations Density 0.027%

    No Known Activations