© 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. 22-LLAMASCOPE-RES-131K
    11. 3682
    Prev
    Next
    INDEX
    Explanations

    names and contact information related to authors or contributors

    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
    ERCHANT
    -0.07
     ac
    -0.06
     ox
    -0.06
    ép
    -0.06
    818
    -0.06
    erral
    -0.05
    isman
    -0.05
    γη
    -0.05
    213
    -0.05
    ý
    -0.05
    POSITIVE LOGITS
     ad
    0.08
    _native
    0.07
     Cannes
    0.07
    anga
    0.07
    лÑĸн
    0.07
     Lump
    0.07
    _measurement
    0.07
    igel
    0.07
    dden
    0.07
    hear
    0.07
    Activations Density 0.003%

    No Known Activations