© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126870
    Prev
    Next
    INDEX
    Explanations

    syntax related to exception handling in programming

    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
    -Saharan
    -0.06
    Ñīин
    -0.06
    oni
    -0.06
    idlo
    -0.06
     Lav
    -0.06
    auen
    -0.06
    è§
    -0.06
     Chris
    -0.06
     دÙģ
    -0.06
    izons
    -0.06
    POSITIVE LOGITS
    abr
    0.09
    ãĥŃãĥ¼
    0.07
    à¹Ģà¸ģล
    0.07
    iв
    0.06
    _gem
    0.06
    apon
    0.06
    DEX
    0.06
    ÅĽcie
    0.06
    ãĤ¤ãĤ¹
    0.06
    :last
    0.06
    Activations Density 0.011%

    No Known Activations