© 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 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. 119224
    Prev
    Next
    INDEX
    Explanations

    expressions related to belief systems and faith perspectives

    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
    uppen
    -0.08
    antino
    -0.07
    lashes
    -0.06
    asca
    -0.06
    683
    -0.06
    ró
    -0.06
    ublic
    -0.06
    antee
    -0.06
    azen
    -0.06
    ErrorException
    -0.06
    POSITIVE LOGITS
     none
    0.20
     nothing
    0.20
     None
    0.18
     no
    0.18
     zero
    0.17
    None
    0.16
     NONE
    0.16
    none
    0.16
    _none
    0.16
    -none
    0.15
    Activations Density 0.184%

    No Known Activations