© 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. 119704
    Prev
    Next
    INDEX
    Explanations

    references to local entities or communities

    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
    .Areas
    -0.07
    /DD
    -0.06
    asp
    -0.06
    orem
    -0.06
    алов
    -0.06
    oad
    -0.06
     nave
    -0.06
    ips
    -0.06
     Blasio
    -0.05
    γγελ
    -0.05
    POSITIVE LOGITS
    /local
    0.10
    /state
    0.08
     town
    0.08
    -local
    0.07
    ,state
    0.07
    craft
    0.07
    -town
    0.07
    /reg
    0.07
    local
    0.07
     local
    0.07
    Activations Density 0.010%

    No Known Activations