© 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. 128135
    Prev
    Next
    INDEX
    Explanations

    URLs or web links 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
     backpage
    -0.09
    apist
    -0.08
    δή
    -0.07
    erdale
    -0.07
    orz
    -0.07
    nock
    -0.07
    воб
    -0.07
    ivot
    -0.07
    yntax
    -0.07
    енÑģ
    -0.07
    POSITIVE LOGITS
     Thi
    0.07
    tin
    0.06
     toys
    0.06
     ease
    0.06
    seudo
    0.05
     Priv
    0.05
     toy
    0.05
     Brun
    0.05
     Sel
    0.05
    imli
    0.05
    Activations Density 0.005%

    No Known Activations