© 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. 9-LLAMASCOPE-RES-131K
    11. 95827
    Prev
    Next
    INDEX
    Explanations

    references to company achievements 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
    acier
    -0.06
    ell
    -0.06
    ETF
    -0.06
     pathMatch
    -0.05
     dib
    -0.05
    ICO
    -0.05
    olumn
    -0.05
     Province
    -0.05
     Sisters
    -0.05
    ico
    -0.05
    POSITIVE LOGITS
    olec
    0.08
    zik
    0.08
    Ïħκ
    0.08
    òi
    0.07
    laus
    0.07
     tròn
    0.07
    LETTE
    0.07
    åĢĻ
    0.07
    avior
    0.07
    -END
    0.07
    Activations Density 0.025%

    No Known Activations