© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 2762
    Prev
    Next
    INDEX
    Explanations

    mentions of relationships or connections between entities

    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
    áºł
    -0.07
    ONTAL
    -0.07
    HING
    -0.06
    reib
    -0.06
    ваÑĤ
    -0.06
    chia
    -0.06
    og
    -0.06
    iferay
    -0.06
    ाà¤ĸ
    -0.06
    _mono
    -0.06
    POSITIVE LOGITS
    surname
    0.06
     kun
    0.06
     Cr
    0.06
     Nadu
    0.06
    enses
    0.06
     Santana
    0.06
    eroon
    0.06
    arton
    0.06
     convention
    0.06
    uars
    0.06
    Activations Density 0.062%

    No Known Activations