© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 87028
    Prev
    Next
    INDEX
    Explanations

    references to time periods and events

    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
     aging
    -0.06
    skb
    -0.06
     Powell
    -0.06
    adem
    -0.06
     stub
    -0.06
     grown
    -0.05
     contemporary
    -0.05
     ageing
    -0.05
    Od
    -0.05
     Od
    -0.05
    POSITIVE LOGITS
     spent
    0.10
    spent
    0.08
     devoted
    0.08
    iger
    0.07
    åĬª
    0.07
    cott
    0.07
    ispiel
    0.07
    -transitional
    0.07
    /Dk
    0.07
    å°¾
    0.07
    Activations Density 0.150%

    No Known Activations