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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 89989
    Prev
    Next
    INDEX
    Explanations

    themes related to cultural opposition and societal controversy

    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
    duk
    -0.08
    _Tis
    -0.08
    apor
    -0.08
    بÙĪاسطة
    -0.07
     addCriterion
    -0.07
    asia
    -0.07
    ÑĥÑĩа
    -0.07
    çŃij
    -0.07
    ãĤ¤ãĥ³ãĥĪ
    -0.07
    리ìĸ´
    -0.07
    POSITIVE LOGITS
     eth
    0.07
    Âł
    0.06
     ec
    0.06
    ,
    0.06
    locker
    0.06
    ensa
    0.06
     Eth
    0.06
     enclosed
    0.06
     disb
    0.05
     represent
    0.05
    Activations Density 0.041%

    No Known Activations