© 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. 90898
    Prev
    Next
    INDEX
    Explanations

    phrases centered around assistance and improving client outcomes

    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
     Cabinet
    -0.06
    och
    -0.06
     spiral
    -0.06
     Va
    -0.06
    Executable
    -0.05
    otor
    -0.05
     cabinet
    -0.05
    /state
    -0.05
     Ped
    -0.05
     Falcon
    -0.05
    POSITIVE LOGITS
    jez
    0.07
    hazi
    0.07
    (help
    0.07
    elter
    0.07
    帮åĬ©
    0.07
    AGIC
    0.07
    ouz
    0.07
    aroo
    0.07
    emaakt
    0.07
    kip
    0.07
    Activations Density 0.029%

    No Known Activations