© 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. 30321
    Prev
    Next
    INDEX
    Explanations

    terms related to exceptions or special permissions

    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
     Carlson
    -0.06
    thes
    -0.06
    amer
    -0.06
    çĽĺ
    -0.06
     cleanly
    -0.06
    igor
    -0.06
     intox
    -0.06
    æĹı
    -0.05
    Compiled
    -0.05
    ún
    -0.05
    POSITIVE LOGITS
    umbo
    0.07
    Äįan
    0.06
    erville
    0.06
    /umd
    0.06
    -toggle
    0.06
    Ń
    0.06
    assic
    0.06
    oldem
    0.06
     (!((
    0.06
    recision
    0.06
    Activations Density 0.000%

    No Known Activations