© 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. 57948
    Prev
    Next
    INDEX
    Explanations

    expressions of love and acceptance

    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
    ,{"
    -0.09
    oir
    -0.09
    uitka
    -0.08
    NAL
    -0.08
    -Agent
    -0.07
    olute
    -0.07
    .EXTRA
    -0.07
    alta
    -0.07
    inka
    -0.07
    覧
    -0.07
    POSITIVE LOGITS
     love
    0.08
     Love
    0.06
     pain
    0.05
    adata
    0.05
    toc
    0.05
     hope
    0.05
     Hubb
    0.05
     rev
    0.05
    Love
    0.05
    æĦĽ
    0.05
    Activations Density 0.034%

    No Known Activations