© 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. 82628
    Prev
    Next
    INDEX
    Explanations

    references to belief, denial of faith, and the relationship between sin and salvation

    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
    ARRIER
    -0.08
    .Automation
    -0.08
     mát
    -0.08
    xec
    -0.07
    _AHB
    -0.07
     chặt
    -0.07
    .readString
    -0.07
    reib
    -0.07
    ÏģιÏĥ
    -0.07
    quette
    -0.07
    POSITIVE LOGITS
     Silver
    0.07
    409
    0.07
     Helm
    0.06
     silver
    0.06
     Ant
    0.06
     Fed
    0.06
     receiving
    0.06
     Or
    0.06
    oot
    0.06
     Goodman
    0.05
    Activations Density 0.003%

    No Known Activations