© 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. 9-LLAMASCOPE-RES-131K
    11. 95698
    Prev
    Next
    INDEX
    Explanations

    loop constructs in programming 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
    ascus
    -0.08
    код
    -0.08
    onica
    -0.08
    upertino
    -0.07
    onso
    -0.07
    perial
    -0.07
    capitalize
    -0.07
    groupon
    -0.07
    GIT
    -0.07
    isor
    -0.07
    POSITIVE LOGITS
     문
    0.06
    line
    0.06
    167
    0.05
    ìį¨
    0.05
    304
    0.05
    677
    0.05
    AndWait
    0.05
    217
    0.05
     же
    0.05
     curs
    0.05
    Activations Density 0.015%

    No Known Activations