© 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. 79604
    Prev
    Next
    INDEX
    Explanations

    social media mentions and engagement indicators

    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
    .appspot
    -0.08
    OrFail
    -0.07
    lider
    -0.07
    .ravel
    -0.07
    oder
    -0.07
    pla
    -0.06
    ipt
    -0.06
    arge
    -0.06
    arges
    -0.06
    ense
    -0.06
    POSITIVE LOGITS
    ldr
    0.06
     (@
    0.06
     Gaming
    0.06
     bóng
    0.06
    -archive
    0.06
    ebek
    0.05
    rens
    0.05
     hourly
    0.05
    deen
    0.05
     AFL
    0.05
    Activations Density 0.008%

    No Known Activations