© 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. 87988
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and personal connection

    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
     [
    -0.06
    ows
    -0.06
     cru
    -0.06
    498
    -0.05
     actually
    -0.05
     or
    -0.05
     Wheeler
    -0.05
     alternate
    -0.05
    or
    -0.05
     degree
    -0.05
    POSITIVE LOGITS
     yours
    0.18
     Yours
    0.13
     YOU
    0.11
     theirs
    0.10
    YOU
    0.10
     YOUR
    0.10
     Ø´Ùħا
    0.10
     ê·Ģ
    0.09
     hers
    0.09
     ours
    0.09
    Activations Density 0.031%

    No Known Activations