© 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. 119831
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to anti-Semitism and related ideological assertions

    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
     Straight
    -0.07
    дап
    -0.06
    ymph
    -0.06
     Pil
    -0.06
    inel
    -0.06
    osph
    -0.06
     Plain
    -0.06
    itsu
    -0.06
     Planned
    -0.06
    мелÑĮ
    -0.06
    POSITIVE LOGITS
    awy
    0.07
    alla
    0.07
    ahy
    0.07
    icit
    0.07
    UCKET
    0.07
    EMENT
    0.07
    ستÙĩ
    0.07
    wert
    0.06
    ãĥIJãĥ¼
    0.06
    wc
    0.06
    Activations Density 0.000%

    No Known Activations