© 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. 15-LLAMASCOPE-RES-131K
    11. 104201
    Prev
    Next
    INDEX
    Explanations

    topics related to various genres of literature and their characteristics

    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
    oret
    -0.07
    quam
    -0.07
    ook
    -0.06
     Hubbard
    -0.06
    اک
    -0.06
    èijĹ
    -0.06
    uest
    -0.06
    RTL
    -0.06
    eler
    -0.06
    Ä
    -0.06
    POSITIVE LOGITS
     cart
    0.07
     Uncategorized
    0.07
    790
    0.07
     treeNode
    0.06
    igsaw
    0.06
     liá»ģn
    0.06
    enstein
    0.06
    Leave
    0.06
     CharSequence
    0.06
    AffineTransform
    0.05
    Activations Density 0.012%

    No Known Activations