© 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. 121195
    Prev
    Next
    INDEX
    Explanations

    concepts related to demons and their interactions with the physical world

    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
    oram
    -0.07
    itom
    -0.07
    çĶ
    -0.07
    ungan
    -0.07
    vez
    -0.07
    جا
    -0.07
    uky
    -0.07
    edis
    -0.07
    illet
    -0.07
    389
    -0.07
    POSITIVE LOGITS
     Ka
    0.07
     "..
    0.06
    PCODE
    0.06
     gro
    0.06
     PCs
    0.06
     Libraries
    0.06
    fst
    0.06
     Gro
    0.06
     sculpt
    0.05
     extrad
    0.05
    Activations Density 0.001%

    No Known Activations