© 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. 75768
    Prev
    Next
    INDEX
    Explanations

    descriptions of emotional and thematic intensity, with a focus on negative connotations

    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
     only
    -0.06
    aliases
    -0.06
     Background
    -0.06
    ason
    -0.06
    016
    -0.05
    etik
    -0.05
    ossa
    -0.05
     Bair
    -0.05
    epad
    -0.05
    .
    -0.05
    POSITIVE LOGITS
    ãĤº
    0.07
    -of
    0.07
    ONTAL
    0.07
    ł
    0.07
    rens
    0.07
    alette
    0.07
    ุษ
    0.07
    reta
    0.07
    /svg
    0.07
    enus
    0.07
    Activations Density 0.051%

    No Known Activations