© 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. 29133
    Prev
    Next
    INDEX
    Explanations

    vertical spacing and formatting elements in the text

    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
    amer
    -0.07
    isc
    -0.06
    ide
    -0.06
    å¹²
    -0.06
    lid
    -0.06
    ustom
    -0.06
    apı
    -0.06
    orman
    -0.06
    ervo
    -0.06
    associate
    -0.06
    POSITIVE LOGITS
    chia
    0.08
    uess
    0.06
    llib
    0.06
     Kush
    0.06
    PIC
    0.06
    Miami
    0.06
    ç£
    0.06
    ække
    0.06
     Erick
    0.06
    arto
    0.06
    Activations Density 0.010%

    No Known Activations