© 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. 17-LLAMASCOPE-RES-131K
    11. 41254
    Prev
    Next
    INDEX
    Explanations

    elements and properties related to HTML and CSS structure

    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
    ãĥ¼ãĥ
    -0.08
    avatars
    -0.07
    izzo
    -0.07
    imir
    -0.07
    sage
    -0.07
    AMED
    -0.07
    NST
    -0.07
    YTE
    -0.07
    inia
    -0.07
    legg
    -0.07
    POSITIVE LOGITS
     Hosp
    0.07
    ico
    0.06
    ateurs
    0.06
    omu
    0.06
    tere
    0.06
     vag
    0.06
    atk
    0.06
     contact
    0.06
     Burb
    0.06
     circ
    0.05
    Activations Density 0.057%

    No Known Activations