© 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. 62140
    Prev
    Next
    INDEX
    Explanations

    programming and configuration syntax elements

    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
     karak
    -0.07
    ]*)
    -0.06
    .appspot
    -0.06
    Benchmark
    -0.06
    owitz
    -0.06
    æĭĶ
    -0.06
    -FIRST
    -0.06
    sein
    -0.06
    ire
    -0.06
    ÑģÑĤвоÑĢ
    -0.06
    POSITIVE LOGITS
    ammer
    0.06
    adder
    0.06
    resar
    0.06
    ACHINE
    0.06
    pluck
    0.06
    ÌĢ
    0.06
    oppel
    0.06
    agger
    0.06
    pline
    0.06
    ÃŃc
    0.06
    Activations Density 0.253%

    No Known Activations