© 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. 129408
    Prev
    Next
    INDEX
    Explanations

    expressions of commitment and purpose in relationships and community

    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
    ovky
    -0.07
    Ïħγ
    -0.07
    uguay
    -0.07
    оÑĤв
    -0.07
    ourcem
    -0.07
    IFEST
    -0.07
    ãĥ¼ãĥĵ
    -0.07
    μαÏĦο
    -0.07
    ongoose
    -0.07
    igan
    -0.07
    POSITIVE LOGITS
     always
    0.07
    ëĭĿ
    0.07
     dust
    0.07
    odor
    0.07
    $LANG
    0.06
     acknow
    0.06
     daily
    0.06
     sil
    0.06
    å§«
    0.06
     flex
    0.06
    Activations Density 0.049%

    No Known Activations