© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5537
    Prev
    Next
    INDEX
    Explanations

    references to political criticism and controversial figures or ideologies

    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
     conservative
    -0.11
     conservatives
    -0.11
     conservatism
    -0.10
     Conservative
    -0.10
     conserv
    -0.09
     Tory
    -0.09
     Conservatives
    -0.08
    Republicans
    -0.08
     Stam
    -0.08
     homophobic
    -0.07
    POSITIVE LOGITS
     leftist
    0.10
     socialist
    0.09
     Communist
    0.09
    -left
    0.09
     socialism
    0.08
     Socialist
    0.08
     Left
    0.08
    /left
    0.08
     Marxist
    0.08
     communist
    0.08
    Activations Density 0.530%

    No Known Activations