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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90428
    Prev
    Next
    INDEX
    Explanations

    references to biblical texts and scripture

    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
    лон
    -0.08
    ADR
    -0.07
    ãĥ¼ãĤ¹ãĥĪ
    -0.07
    oltip
    -0.07
    _VENDOR
    -0.07
    iec
    -0.07
     dahi
    -0.07
    ugas
    -0.07
    presso
    -0.07
     OVERRIDE
    -0.07
    POSITIVE LOGITS
    agg
    0.06
     Maher
    0.06
    DataSetChanged
    0.06
    arrant
    0.06
    sez
    0.06
    <typeof
    0.06
     Cher
    0.06
    orro
    0.06
    èµı
    0.05
    esium
    0.05
    Activations Density 0.004%

    No Known Activations