© 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. 1279
    Prev
    Next
    INDEX
    Explanations

    aspects related to service and partnerships

    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
     Affero
    -0.07
    ase
    -0.07
    WindowState
    -0.07
    atatype
    -0.07
    odash
    -0.07
    .scalablytyped
    -0.07
    ÑĤап
    -0.07
    squ
    -0.06
    ứng
    -0.06
    поÑĢ
    -0.06
    POSITIVE LOGITS
    tras
    0.06
    hek
    0.05
     Seeking
    0.05
    icht
    0.05
    rypt
    0.05
    ision
    0.05
     Brend
    0.05
    qrt
    0.05
     Hud
    0.05
    folk
    0.05
    Activations Density 0.052%

    No Known Activations