© 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. 15-LLAMASCOPE-RES-131K
    6. 1334
    Prev
    Next
    INDEX
    Explanations

    unusual or special characters and symbols

    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
    ÃŃsto
    -0.08
    ayah
    -0.08
    ¶Į
    -0.08
    aju
    -0.07
    anan
    -0.07
    ushima
    -0.07
    çķ
    -0.07
    áÄį
    -0.07
    erton
    -0.07
    ialis
    -0.07
    POSITIVE LOGITS
    teg
    0.06
    tek
    0.06
    omics
    0.06
    lect
    0.06
     Pep
    0.06
    rance
    0.06
    RL
    0.06
    \Collections
    0.06
    su
    0.05
    eking
    0.05
    Activations Density 0.000%

    No Known Activations