© 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. 104175
    Prev
    Next
    INDEX
    Explanations

    mentions of copyright and licensing terms

    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
    ctor
    -0.07
    242
    -0.07
    -0.06
    ingu
    -0.06
    indsight
    -0.06
    ét
    -0.06
    avy
    -0.06
    é
    -0.06
    guard
    -0.06
    isse
    -0.05
    POSITIVE LOGITS
    -SA
    0.08
    LEGRO
    0.08
    dda
    0.08
     âĹĦ
    0.07
    ungan
    0.07
     вок
    0.07
    -instance
    0.07
    иÑĤов
    0.07
    Îļα
    0.07
    arkin
    0.07
    Activations Density 0.003%

    No Known Activations