© 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. 41220
    Prev
    Next
    INDEX
    Explanations

    line breaks or new sections in the text

    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
    ↵
    -0.07
    nda
    -0.07
    usi
    -0.06
    utton
    -0.06
     Marketable
    -0.06
    564
    -0.06
    041
    -0.06
    hed
    -0.06
    entials
    -0.06
    UIL
    -0.06
    POSITIVE LOGITS
    ernes
    0.07
     ï¼ļ
    0.07
    ÙĥÙĨ
    0.07
     encount
    0.07
     Van
    0.07
    ahlen
    0.07
    Ế
    0.07
    λή
    0.06
    .Dom
    0.06
     célib
    0.06
    Activations Density 0.000%

    No Known Activations