© 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. 944
    Prev
    Next
    INDEX
    Explanations

    references to constitutional amendments and legal rights

    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
    sey
    -0.07
    ordon
    -0.07
    zelf
    -0.07
    IMO
    -0.07
    scape
    -0.06
     Tone
    -0.06
    lernen
    -0.06
    setSize
    -0.06
    sie
    -0.06
    sun
    -0.06
    POSITIVE LOGITS
    aires
    0.08
    reuse
    0.06
     to
    0.06
    iros
    0.06
     Pell
    0.06
    $MESS
    0.06
     Drivers
    0.06
    ÑĥлÑĮÑĤа
    0.06
    aign
    0.06
    YPE
    0.06
    Activations Density 0.004%

    No Known Activations