© 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. 29449
    Prev
    Next
    INDEX
    Explanations

    references to regulatory and compliance-related content

    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
     US
    -0.06
     coun
    -0.06
    ê°ķ
    -0.06
     counselor
    -0.06
    oust
    -0.06
    ills
    -0.05
     molds
    -0.05
     copyrighted
    -0.05
     Wenger
    -0.05
     Damon
    -0.05
    POSITIVE LOGITS
    Serializable
    0.08
    PUTE
    0.07
    еÑĢин
    0.07
     Weston
    0.07
     Loved
    0.07
     Raq
    0.07
    æ
    0.07
    ´Ģ
    0.07
    BAT
    0.07
     Midlands
    0.07
    Activations Density 0.002%

    No Known Activations