© 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. 26457
    Prev
    Next
    INDEX
    Explanations

    concepts related to control and the limitations people face in their lives

    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
    meden
    -0.07
    Ñģол
    -0.07
    reau
    -0.07
    ROUP
    -0.07
    Ľi
    -0.06
    iben
    -0.06
    igm
    -0.06
    INA
    -0.06
    ıda
    -0.06
    disposing
    -0.06
    POSITIVE LOGITS
    ocht
    0.09
    /control
    0.08
     control
    0.08
    control
    0.07
     Control
    0.07
    avel
    0.07
    ÏĨεÏģ
    0.07
    Control
    0.07
    Accent
    0.06
    (control
    0.06
    Activations Density 0.009%

    No Known Activations