© 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. 70506
    Prev
    Next
    INDEX
    Explanations

    words related to various types of "-ism" concepts or tendencies

    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
    zilla
    -0.08
    iÄįka
    -0.07
    ÑĩиÑĤ
    -0.07
    chap
    -0.07
    inine
    -0.07
     geil
    -0.07
    tober
    -0.07
    anson
    -0.07
    ýt
    -0.07
    amination
    -0.06
    POSITIVE LOGITS
    keit
    0.08
    oux
    0.07
    dale
    0.07
    emma
    0.06
    otle
    0.06
    otent
    0.06
    opher
    0.06
    ear
    0.06
    dling
    0.06
     myself
    0.06
    Activations Density 0.034%

    No Known Activations