© 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. 3000
    Prev
    Next
    INDEX
    Explanations

    references to significant events and organizational structures

    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
     Morgan
    -0.06
     Piper
    -0.06
     Britain
    -0.06
     Twe
    -0.06
     taught
    -0.06
     fish
    -0.06
    entiful
    -0.06
    anim
    -0.06
    ãģĨãģ¡
    -0.05
     nationwide
    -0.05
    POSITIVE LOGITS
    Delegate
    0.07
    odash
    0.07
    inden
    0.07
     deleg
    0.07
    _firestore
    0.07
    .scalablytyped
    0.07
    FormatException
    0.07
    ewith
    0.07
    irut
    0.07
    åĨ°
    0.07
    Activations Density 0.004%

    No Known Activations