© 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. 17-LLAMASCOPE-RES-131K
    11. 38795
    Prev
    Next
    INDEX
    Explanations

    establishments and projects related to recreational facilities and public constructions

    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
    ãģ°ãģĭãĤĬ
    -0.08
    -alist
    -0.07
    ELLOW
    -0.07
    lingen
    -0.07
    rott
    -0.07
    entes
    -0.06
    andest
    -0.06
    ifecycle
    -0.06
    REEN
    -0.06
     nues
    -0.06
    POSITIVE LOGITS
     project
    0.10
     proposal
    0.07
    ingleton
    0.07
    project
    0.07
     proposed
    0.07
    é¡¹çĽ®
    0.07
     proposals
    0.06
     planned
    0.06
    ylon
    0.06
     plans
    0.06
    Activations Density 0.036%

    No Known Activations