© 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. 61414
    Prev
    Next
    INDEX
    Explanations

    keywords related to media partnerships and collaborations

    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
     fas
    -0.07
    ILLISE
    -0.06
     Marketable
    -0.06
     erotisch
    -0.06
    vest
    -0.06
    меÑĪ
    -0.06
    ropoda
    -0.06
    çIJ³
    -0.06
    quat
    -0.06
    ovie
    -0.06
    POSITIVE LOGITS
     partners
    0.07
     parten
    0.07
     partner
    0.07
    partner
    0.06
     Exact
    0.06
    'gc
    0.06
    odom
    0.06
    utut
    0.06
     elsewhere
    0.06
     Silent
    0.06
    Activations Density 0.033%

    No Known Activations