© 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. 62505
    Prev
    Next
    INDEX
    Explanations

    negative phrases or concepts related to failure and dissatisfaction

    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
    Decoration
    -0.08
    ãĤ¥
    -0.07
     eskort
    -0.07
    thro
    -0.07
    boru
    -0.07
    thouse
    -0.07
    OMIC
    -0.07
    ãĥ¼ãĥ
    -0.07
    MOOTH
    -0.07
    quared
    -0.07
    POSITIVE LOGITS
    olson
    0.06
     casc
    0.06
     prest
    0.06
    kel
    0.06
     of
    0.06
     Bauer
    0.06
     Pav
    0.06
    ogan
    0.06
     Alter
    0.05
    HING
    0.05
    Activations Density 0.014%

    No Known Activations