© 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. 5-LLAMASCOPE-RES-131K
    6. 125844
    Prev
    Next
    INDEX
    Explanations

    words related to love and romantic themes

    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
    .scalablytyped
    -0.10
    idar
    -0.08
    arine
    -0.07
    elope
    -0.06
    iff
    -0.06
    irling
    -0.06
    ird
    -0.06
    pan
    -0.06
    icap
    -0.06
    asaki
    -0.06
    POSITIVE LOGITS
    chio
    0.08
    Ïįν
    0.06
    etimes
    0.06
    ÑħÑĥ
    0.06
    los
    0.06
    ازÛĮ
    0.06
    -kind
    0.06
     Bryan
    0.06
    inds
    0.06
    indow
    0.06
    Activations Density 0.004%

    No Known Activations