© 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. 40052
    Prev
    Next
    INDEX
    Explanations

    references to faith and religious beliefs

    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
    elu
    -0.08
     councill
    -0.06
    Kir
    -0.06
     skoro
    -0.06
    aml
    -0.06
     Sage
    -0.06
    996
    -0.06
    kan
    -0.06
    errer
    -0.06
    ãĥ³ãĥĶ
    -0.06
    POSITIVE LOGITS
     Evidence
    0.07
    arrant
    0.07
     evidence
    0.07
    èĩ£
    0.06
     BaseType
    0.06
     Daw
    0.06
    Evidence
    0.06
     evid
    0.06
     grounds
    0.06
    nock
    0.06
    Activations Density 0.009%

    No Known Activations