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

    Neuronpedia

    Jacobian LensNEW
    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. 119261
    Prev
    Next
    INDEX
    Explanations

    mentions of "Amazon" and its related services

    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
    858
    -0.07
    .Unicode
    -0.07
    ritz
    -0.06
    sy
    -0.06
    StackSize
    -0.06
    aber
    -0.06
     Jacob
    -0.06
    LastError
    -0.06
    finity
    -0.06
     rau
    -0.06
    POSITIVE LOGITS
    ian
    0.10
    ijken
    0.08
    ians
    0.08
    .com
    0.08
     Ballard
    0.08
    /place
    0.07
    culate
    0.07
    Bas
    0.07
     AWS
    0.07
    arendra
    0.07
    Activations Density 0.004%

    No Known Activations