© 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. 80484
    Prev
    Next
    INDEX
    Explanations

    references to a specific location or region, particularly "Columbus."

    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
    åij½
    -0.08
    htable
    -0.08
    ivate
    -0.08
    kola
    -0.08
    ril
    -0.08
    lemen
    -0.08
    abal
    -0.07
    ÙħÙĨد
    -0.07
    yonel
    -0.07
    abwe
    -0.07
    POSITIVE LOGITS
    hed
    0.07
    rah
    0.06
    ar
    0.06
    oston
    0.06
     ÙģÙĤ
    0.06
    ether
    0.06
     baj
    0.06
    atoi
    0.06
    etta
    0.06
    bian
    0.06
    Activations Density 0.007%

    No Known Activations