© 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. 103280
    Prev
    Next
    INDEX
    Explanations

    adjectives and phrases that indicate quality, value, and the nature of actions or situations

    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
    /preferences
    -0.07
    tml
    -0.07
    ãĤıãģĽ
    -0.07
    tek
    -0.07
    .onCreate
    -0.06
    ason
    -0.06
    glob
    -0.06
    ;element
    -0.06
    /*/
    -0.06
     Void
    -0.06
    POSITIVE LOGITS
     manner
    0.10
     ways
    0.09
     fashion
    0.08
     way
    0.07
    LOAT
    0.06
    orex
    0.06
    apes
    0.06
     Elis
    0.06
    ways
    0.06
     Fashion
    0.06
    Activations Density 0.023%

    No Known Activations