© 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. 107116
    Prev
    Next
    INDEX
    Explanations

    phrases indicating global awareness or action

    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
    etxt
    -0.07
    abra
    -0.06
     bour
    -0.06
    agna
    -0.06
    bah
    -0.06
    izador
    -0.06
    айд
    -0.06
    iya
    -0.06
    omanip
    -0.06
     sad
    -0.06
    POSITIVE LOGITS
     profits
    0.07
     PROFITS
    0.07
     Bulls
    0.07
    IMENT
    0.06
    rames
    0.06
    رÙĪد
    0.06
    мож
    0.06
    ãģŀ
    0.06
    dos
    0.06
    796
    0.06
    Activations Density 0.000%

    No Known Activations