© 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. 129838
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of opinion manipulation and critique of belief systems

    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
    emma
    -0.07
    ekler
    -0.06
    578
    -0.06
     Vale
    -0.06
    ÄĽle
    -0.06
     kes
    -0.05
    zp
    -0.05
    ersh
    -0.05
    hi
    -0.05
    141
    -0.05
    POSITIVE LOGITS
     anything
    0.17
    anything
    0.16
     Anything
    0.15
    Anything
    0.15
     everything
    0.13
     ANY
    0.13
    everything
    0.13
    _any
    0.12
     Everything
    0.11
     cualquier
    0.11
    Activations Density 0.042%

    No Known Activations