© 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. 1203
    Prev
    Next
    INDEX
    Explanations

    references to video content and viewer feedback

    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
     pl
    -0.07
     popular
    -0.06
     Paid
    -0.06
    edia
    -0.06
    ung
    -0.06
     paid
    -0.06
     isolated
    -0.06
    ler
    -0.05
    bas
    -0.05
     fond
    -0.05
    POSITIVE LOGITS
    gua
    0.08
    ".$_
    0.08
    idelity
    0.07
    kün
    0.07
    ittal
    0.07
    uilder
    0.07
    SizePolicy
    0.07
    )((((
    0.07
    hread
    0.07
    ectl
    0.07
    Activations Density 0.035%

    No Known Activations