© 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. 17-LLAMASCOPE-RES-131K
    11. 3951
    Prev
    Next
    INDEX
    Explanations

    references to the Holy Spirit and its actions

    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
    apgolly
    -0.08
    antha
    -0.08
    èħķ
    -0.07
    thag
    -0.07
    .deck
    -0.07
    .lift
    -0.07
    ække
    -0.07
    озем
    -0.07
     NavParams
    -0.07
    odem
    -0.07
    POSITIVE LOGITS
     conv
    0.08
     rev
    0.06
     Revel
    0.06
     gust
    0.06
     Conv
    0.06
    conv
    0.06
     Pent
    0.06
     Comfort
    0.06
     drawing
    0.06
    ึà¸ĩ
    0.05
    Activations Density 0.009%

    No Known Activations