© 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. 106926
    Prev
    Next
    INDEX
    Explanations

    technical terms related to location, navigation, and measurement

    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
    anga
    -0.06
    .scalablytyped
    -0.06
    917
    -0.06
    497
    -0.06
    238
    -0.06
     precise
    -0.06
    ominator
    -0.06
    477
    -0.06
     ir
    -0.06
    955
    -0.06
    POSITIVE LOGITS
    ож
    0.06
    heure
    0.06
    geben
    0.06
    klär
    0.06
    kus
    0.06
    bourne
    0.06
    BILE
    0.06
    té
    0.06
    rå
    0.06
    RF
    0.06
    Activations Density 0.001%

    No Known Activations