© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 125948
    Prev
    Next
    INDEX
    Explanations

    syntactical structure indicators in programming or markup languages

    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
    ujet
    -0.07
     Neutral
    -0.06
    839
    -0.06
    и
    -0.06
    854
    -0.06
    ensi
    -0.06
    149
    -0.06
    itin
    -0.06
    353
    -0.06
     neutral
    -0.06
    POSITIVE LOGITS
    inand
    0.07
    Ymd
    0.07
    .scalablytyped
    0.07
    htm
    0.06
    undle
    0.06
     prov
    0.06
    otland
    0.06
    PUR
    0.06
    /Dk
    0.06
    pur
    0.06
    Activations Density 0.041%

    No Known Activations