© 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. 56219
    Prev
    Next
    INDEX
    Explanations

    references to citations and academic formatting in a research context

    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
    oru
    -0.07
    orum
    -0.07
    TRL
    -0.07
     lô
    -0.06
    etest
    -0.06
    upo
    -0.06
     CÆ¡
    -0.06
     Lust
    -0.06
     æ¼
    -0.06
    lap
    -0.06
    POSITIVE LOGITS
    ceph
    0.07
    alf
    0.06
    ills
    0.06
    aina
    0.06
    .blogspot
    0.06
    iew
    0.06
    ews
    0.06
    ÙģاÙĤ
    0.06
    lector
    0.06
    946
    0.06
    Activations Density 0.027%

    No Known Activations