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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117468
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to religion and cultural heritage

    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
    friend
    -0.07
    pron
    -0.07
    pliers
    -0.07
    ette
    -0.06
    ottage
    -0.06
    _REPLY
    -0.06
    prene
    -0.06
    uros
    -0.06
    ninger
    -0.06
    xx
    -0.06
    POSITIVE LOGITS
    filt
    0.07
    -leaning
    0.07
    625
    0.06
    agher
    0.06
    ÏĦολ
    0.06
     disap
    0.06
    -Sah
    0.06
    596
    0.06
    antine
    0.06
    à¹Ģà¸Ħล
    0.06
    Activations Density 0.017%

    No Known Activations