© 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. 84384
    Prev
    Next
    INDEX
    Explanations

    references to pictures and images

    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
    ych
    -0.07
    642
    -0.07
    ↵
    -0.06
    ter
    -0.06
    std
    -0.06
    ami
    -0.06
     d
    -0.06
    owitz
    -0.06
     Rip
    -0.06
    uk
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.10
    еÑĢин
    0.08
    icontrol
    0.07
    "class
    0.07
    iddet
    0.07
     Bunu
    0.07
     Gür
    0.07
    byt
    0.07
    بÙĪاسطة
    0.07
    Ħĸ
    0.07
    Activations Density 0.000%

    No Known Activations