© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125251
    Prev
    Next
    INDEX
    Explanations

    references to technology and specific industries

    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
    theless
    -0.07
    soever
    -0.06
     详æĥħ
    -0.06
     Yet
    -0.06
     nhau
    -0.06
    ohl
    -0.05
    ÏĦζ
    -0.05
     Angiosper
    -0.05
    ges
    -0.05
    .context
    -0.05
    POSITIVE LOGITS
    ìļ©
    0.08
    PFN
    0.07
    ekim
    0.07
    andles
    0.07
     Wahl
    0.07
    osaur
    0.07
    umann
    0.07
    _Internal
    0.07
    -addons
    0.07
    arseille
    0.06
    Activations Density 0.082%

    No Known Activations