© 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 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. 29025
    Prev
    Next
    INDEX
    Explanations

    themes related to censorship and the suppression of public expression

    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
    atsu
    -0.07
    ÑĢаÑģÑĤ
    -0.07
    รà¸ĵ
    -0.07
    á»Ļ
    -0.07
    ủ
    -0.07
    ĻĤ
    -0.06
     ún
    -0.06
    äºĽ
    -0.06
    isch
    -0.06
    áo
    -0.06
    POSITIVE LOGITS
     perfectly
    0.09
     nowhere
    0.08
     God
    0.06
    Ħĸ
    0.06
     Leg
    0.06
     legitimate
    0.06
    God
    0.06
    0.06
     repeatedly
    0.06
    ebra
    0.06
    Activations Density 0.038%

    No Known Activations