© 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. 82148
    Prev
    Next
    INDEX
    Explanations

    expressions of personal faith and commitment to God

    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
    oba
    -0.07
    eve
    -0.07
    _MARKER
    -0.07
    dum
    -0.07
    ¼
    -0.07
    uzzer
    -0.06
    NG
    -0.06
    adia
    -0.06
    ÑĸлÑĮ
    -0.06
    åľ¨çº¿è§Ĥçľĭ
    -0.06
    POSITIVE LOGITS
    //{{
    0.07
     God
    0.07
    ToStr
    0.07
    ÅĻÃŃz
    0.06
    mpp
    0.06
     him
    0.06
    -thumb
    0.06
    Äįer
    0.06
    osaic
    0.06
     Convers
    0.06
    Activations Density 0.018%

    No Known Activations