© 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. 17-LLAMASCOPE-RES-131K
    11. 84770
    Prev
    Next
    INDEX
    Explanations

    cozy and comforting domestic scenes

    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
     sept
    -0.06
    afa
    -0.06
    izu
    -0.06
    lyph
    -0.06
     Pr
    -0.06
    defgroup
    -0.06
    NCY
    -0.06
     reform
    -0.05
     ro
    -0.05
     speech
    -0.05
    POSITIVE LOGITS
     ÑĢÑĥÑĩ
    0.08
     cozy
    0.07
     haul
    0.07
    .fire
    0.07
    issant
    0.07
     overst
    0.07
    artner
    0.07
     ActionController
    0.07
    uru
    0.07
     gord
    0.07
    Activations Density 0.021%

    No Known Activations