© 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. 120192
    Prev
    Next
    INDEX
    Explanations

    specific patterns or inconsistencies in technical or programming-related terms

    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
    511
    -0.06
     Pik
    -0.06
    452
    -0.06
    fts
    -0.06
    riba
    -0.06
    223
    -0.05
     Lost
    -0.05
    ivol
    -0.05
    igans
    -0.05
    453
    -0.05
    POSITIVE LOGITS
    iš
    0.08
    apos
    0.08
    ebek
    0.07
    acky
    0.07
    Ø´
    0.07
    ÑĤÑİ
    0.07
    esktop
    0.07
    ади
    0.07
    ovie
    0.07
    ÏĦοÏħÏĤ
    0.07
    Activations Density 0.018%

    No Known Activations