© 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. 76007
    Prev
    Next
    INDEX
    Explanations

    instructions or steps for completing a process

    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
    erson
    -0.06
    anches
    -0.06
     Containers
    -0.06
    ẻ
    -0.06
    å°ģ
    -0.05
    ody
    -0.05
     abbrev
    -0.05
     zv
    -0.05
     Elephant
    -0.05
     Zip
    -0.05
    POSITIVE LOGITS
     exactly
    0.08
    æŃ£ç¡®
    0.07
    .GroupLayout
    0.07
     jadx
    0.07
    orman
    0.07
    ¦¬
    0.07
     Format
    0.07
    exact
    0.07
    NCY
    0.07
    AGMENT
    0.07
    Activations Density 0.019%

    No Known Activations