© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103718
    Prev
    Next
    INDEX
    Explanations

    references to anti-Semitism and its connections to social justice rhetoric

    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
    opoulos
    -0.07
     requestOptions
    -0.07
    mpp
    -0.07
    Uvs
    -0.06
    riad
    -0.06
    LPARAM
    -0.06
    enko
    -0.06
    476
    -0.06
    ckill
    -0.06
    eman
    -0.06
    POSITIVE LOGITS
     worldwide
    0.08
     spor
    0.07
     СовеÑĤ
    0.06
     Worldwide
    0.06
    971
    0.06
    ãĥ³ãĥĦ
    0.06
     Sho
    0.06
    edin
    0.06
    820
    0.06
    retty
    0.06
    Activations Density 0.040%

    No Known Activations