Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4927
    Prev
    Next
    INDEX
    Explanations

    programming code or syntax-related elements

    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
    ients
    -0.06
    geist
    -0.06
    eder
    -0.06
    itti
    -0.06
    edium
    -0.06
     Rodrig
    -0.05
    yonel
    -0.05
     Camb
    -0.05
    onna
    -0.05
     pand
    -0.05
    POSITIVE LOGITS
    .jar
    0.08
    ä¸Ī
    0.08
     Thornton
    0.08
    .ribbon
    0.07
    .grp
    0.07
    ãĥ³ãĤ°
    0.07
    :null
    0.07
     кожного
    0.07
    esor
    0.07
    kie
    0.07
    Activations Density 0.000%

    No Known Activations