© 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. 125115
    Prev
    Next
    INDEX
    Explanations

    references to the sale and marketing of products, particularly sugary drinks and chemicals, along with associated regulatory concerns

    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
    anmar
    -0.08
    ä¾
    -0.08
    Äįan
    -0.07
    ubic
    -0.07
     pÅĻist
    -0.07
    anzi
    -0.07
    decorators
    -0.07
    <article
    -0.07
    "math
    -0.07
    _subscribe
    -0.07
    POSITIVE LOGITS
     ped
    0.06
     clear
    0.06
     Ron
    0.06
    wall
    0.05
    ä¸įåĪ°
    0.05
    BuilderInterface
    0.05
     Mot
    0.05
     Hem
    0.05
    edin
    0.05
    ãĥŃãĥ³
    0.05
    Activations Density 0.001%

    No Known Activations