Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96143
    Prev
    Next
    INDEX
    Explanations

    references to Islamic teachings and theological concepts

    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
    elden
    -0.06
    ettel
    -0.06
     Clifford
    -0.06
     ins
    -0.06
    oir
    -0.06
    arrera
    -0.06
    gas
    -0.05
    Ñİк
    -0.05
    ports
    -0.05
     gri
    -0.05
    POSITIVE LOGITS
    angu
    0.07
    ORY
    0.07
    _fu
    0.07
     Äijình
    0.06
     âŁ
    0.06
    รà¸ģ
    0.06
    bind
    0.06
    окол
    0.06
    adro
    0.06
    ugin
    0.06
    Activations Density 0.021%

    No Known Activations