© 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 EvalsExportsinterp-engineNEWAPI 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. 2654
    Prev
    Next
    INDEX
    Explanations

    references to affiliate marketing and sales transactions

    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
    -Clause
    -0.07
    lator
    -0.06
    erator
    -0.06
    efon
    -0.06
    âte
    -0.06
    å³°
    -0.06
    /devices
    -0.06
    abama
    -0.06
    blr
    -0.05
    aci
    -0.05
    POSITIVE LOGITS
     editorial
    0.08
     independ
    0.08
     Independ
    0.08
    Editors
    0.08
    Independ
    0.08
     Editorial
    0.07
     independence
    0.07
    baum
    0.07
    AFX
    0.07
    uin
    0.07
    Activations Density 0.006%

    No Known Activations