© 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. 4288
    Prev
    Next
    INDEX
    Explanations

    references to the influence and impact of Islam on various aspects of West African society, including education and socio-political life

    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
    ait
    -0.07
    chem
    -0.06
    λμ
    -0.06
     newly
    -0.06
    cko
    -0.06
    rarian
    -0.06
    imestone
    -0.06
    VOKE
    -0.06
     GENERATED
    -0.06
    áºŃy
    -0.05
    POSITIVE LOGITS
    adopt
    0.08
    AMY
    0.07
     disproportionate
    0.07
    ADV
    0.07
     adopted
    0.07
    ä¸ĺ
    0.07
    argin
    0.06
    kovou
    0.06
    unga
    0.06
     adopt
    0.06
    Activations Density 0.021%

    No Known Activations