© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 59226
    Prev
    Next
    INDEX
    Explanations

    references to academic publications and citations

    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
    ekil
    -0.06
    iz
    -0.06
    zo
    -0.06
    گاÙĩ
    -0.06
     pr
    -0.06
    ez
    -0.06
    apter
    -0.06
    463
    -0.06
    ses
    -0.05
    ži
    -0.05
    POSITIVE LOGITS
     adipiscing
    0.08
    /Open
    0.07
    ÙĬÙĦØ©
    0.07
    社
    0.07
    hoo
    0.07
    ØŃاد
    0.07
     Belt
    0.07
    кÑĢаÑĹ
    0.07
     khuôn
    0.07
    iná
    0.07
    Activations Density 0.001%

    No Known Activations